Coverage Report

Created: 2025-06-13 07:07

/src/aom/av1/decoder/grain_synthesis.c
Line
Count
Source (jump to first uncovered line)
1
/*
2
 * Copyright (c) 2016, Alliance for Open Media. All rights reserved.
3
 *
4
 * This source code is subject to the terms of the BSD 2 Clause License and
5
 * the Alliance for Open Media Patent License 1.0. If the BSD 2 Clause License
6
 * was not distributed with this source code in the LICENSE file, you can
7
 * obtain it at www.aomedia.org/license/software. If the Alliance for Open
8
 * Media Patent License 1.0 was not distributed with this source code in the
9
 * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
10
 */
11
12
/*!\file
13
 * \brief Describes film grain parameters and film grain synthesis
14
 *
15
 */
16
17
#include <stdbool.h>
18
#include <stdio.h>
19
#include <string.h>
20
#include <stdlib.h>
21
#include <assert.h>
22
#include "aom_dsp/aom_dsp_common.h"
23
#include "aom_mem/aom_mem.h"
24
#include "av1/decoder/grain_synthesis.h"
25
26
// Samples with Gaussian distribution in the range of [-2048, 2047] (12 bits)
27
// with zero mean and standard deviation of about 512.
28
// should be divided by 4 for 10-bit range and 16 for 8-bit range.
29
static const int gaussian_sequence[2048] = {
30
  56,    568,   -180,  172,   124,   -84,   172,   -64,   -900,  24,   820,
31
  224,   1248,  996,   272,   -8,    -916,  -388,  -732,  -104,  -188, 800,
32
  112,   -652,  -320,  -376,  140,   -252,  492,   -168,  44,    -788, 588,
33
  -584,  500,   -228,  12,    680,   272,   -476,  972,   -100,  652,  368,
34
  432,   -196,  -720,  -192,  1000,  -332,  652,   -136,  -552,  -604, -4,
35
  192,   -220,  -136,  1000,  -52,   372,   -96,   -624,  124,   -24,  396,
36
  540,   -12,   -104,  640,   464,   244,   -208,  -84,   368,   -528, -740,
37
  248,   -968,  -848,  608,   376,   -60,   -292,  -40,   -156,  252,  -292,
38
  248,   224,   -280,  400,   -244,  244,   -60,   76,    -80,   212,  532,
39
  340,   128,   -36,   824,   -352,  -60,   -264,  -96,   -612,  416,  -704,
40
  220,   -204,  640,   -160,  1220,  -408,  900,   336,   20,    -336, -96,
41
  -792,  304,   48,    -28,   -1232, -1172, -448,  104,   -292,  -520, 244,
42
  60,    -948,  0,     -708,  268,   108,   356,   -548,  488,   -344, -136,
43
  488,   -196,  -224,  656,   -236,  -1128, 60,    4,     140,   276,  -676,
44
  -376,  168,   -108,  464,   8,     564,   64,    240,   308,   -300, -400,
45
  -456,  -136,  56,    120,   -408,  -116,  436,   504,   -232,  328,  844,
46
  -164,  -84,   784,   -168,  232,   -224,  348,   -376,  128,   568,  96,
47
  -1244, -288,  276,   848,   832,   -360,  656,   464,   -384,  -332, -356,
48
  728,   -388,  160,   -192,  468,   296,   224,   140,   -776,  -100, 280,
49
  4,     196,   44,    -36,   -648,  932,   16,    1428,  28,    528,  808,
50
  772,   20,    268,   88,    -332,  -284,  124,   -384,  -448,  208,  -228,
51
  -1044, -328,  660,   380,   -148,  -300,  588,   240,   540,   28,   136,
52
  -88,   -436,  256,   296,   -1000, 1400,  0,     -48,   1056,  -136, 264,
53
  -528,  -1108, 632,   -484,  -592,  -344,  796,   124,   -668,  -768, 388,
54
  1296,  -232,  -188,  -200,  -288,  -4,    308,   100,   -168,  256,  -500,
55
  204,   -508,  648,   -136,  372,   -272,  -120,  -1004, -552,  -548, -384,
56
  548,   -296,  428,   -108,  -8,    -912,  -324,  -224,  -88,   -112, -220,
57
  -100,  996,   -796,  548,   360,   -216,  180,   428,   -200,  -212, 148,
58
  96,    148,   284,   216,   -412,  -320,  120,   -300,  -384,  -604, -572,
59
  -332,  -8,    -180,  -176,  696,   116,   -88,   628,   76,    44,   -516,
60
  240,   -208,  -40,   100,   -592,  344,   -308,  -452,  -228,  20,   916,
61
  -1752, -136,  -340,  -804,  140,   40,    512,   340,   248,   184,  -492,
62
  896,   -156,  932,   -628,  328,   -688,  -448,  -616,  -752,  -100, 560,
63
  -1020, 180,   -800,  -64,   76,    576,   1068,  396,   660,   552,  -108,
64
  -28,   320,   -628,  312,   -92,   -92,   -472,  268,   16,    560,  516,
65
  -672,  -52,   492,   -100,  260,   384,   284,   292,   304,   -148, 88,
66
  -152,  1012,  1064,  -228,  164,   -376,  -684,  592,   -392,  156,  196,
67
  -524,  -64,   -884,  160,   -176,  636,   648,   404,   -396,  -436, 864,
68
  424,   -728,  988,   -604,  904,   -592,  296,   -224,  536,   -176, -920,
69
  436,   -48,   1176,  -884,  416,   -776,  -824,  -884,  524,   -548, -564,
70
  -68,   -164,  -96,   692,   364,   -692,  -1012, -68,   260,   -480, 876,
71
  -1116, 452,   -332,  -352,  892,   -1088, 1220,  -676,  12,    -292, 244,
72
  496,   372,   -32,   280,   200,   112,   -440,  -96,   24,    -644, -184,
73
  56,    -432,  224,   -980,  272,   -260,  144,   -436,  420,   356,  364,
74
  -528,  76,    172,   -744,  -368,  404,   -752,  -416,  684,   -688, 72,
75
  540,   416,   92,    444,   480,   -72,   -1416, 164,   -1172, -68,  24,
76
  424,   264,   1040,  128,   -912,  -524,  -356,  64,    876,   -12,  4,
77
  -88,   532,   272,   -524,  320,   276,   -508,  940,   24,    -400, -120,
78
  756,   60,    236,   -412,  100,   376,   -484,  400,   -100,  -740, -108,
79
  -260,  328,   -268,  224,   -200,  -416,  184,   -604,  -564,  -20,  296,
80
  60,    892,   -888,  60,    164,   68,    -760,  216,   -296,  904,  -336,
81
  -28,   404,   -356,  -568,  -208,  -1480, -512,  296,   328,   -360, -164,
82
  -1560, -776,  1156,  -428,  164,   -504,  -112,  120,   -216,  -148, -264,
83
  308,   32,    64,    -72,   72,    116,   176,   -64,   -272,  460,  -536,
84
  -784,  -280,  348,   108,   -752,  -132,  524,   -540,  -776,  116,  -296,
85
  -1196, -288,  -560,  1040,  -472,  116,   -848,  -1116, 116,   636,  696,
86
  284,   -176,  1016,  204,   -864,  -648,  -248,  356,   972,   -584, -204,
87
  264,   880,   528,   -24,   -184,  116,   448,   -144,  828,   524,  212,
88
  -212,  52,    12,    200,   268,   -488,  -404,  -880,  824,   -672, -40,
89
  908,   -248,  500,   716,   -576,  492,   -576,  16,    720,   -108, 384,
90
  124,   344,   280,   576,   -500,  252,   104,   -308,  196,   -188, -8,
91
  1268,  296,   1032,  -1196, 436,   316,   372,   -432,  -200,  -660, 704,
92
  -224,  596,   -132,  268,   32,    -452,  884,   104,   -1008, 424,  -1348,
93
  -280,  4,     -1168, 368,   476,   696,   300,   -8,    24,    180,  -592,
94
  -196,  388,   304,   500,   724,   -160,  244,   -84,   272,   -256, -420,
95
  320,   208,   -144,  -156,  156,   364,   452,   28,    540,   316,  220,
96
  -644,  -248,  464,   72,    360,   32,    -388,  496,   -680,  -48,  208,
97
  -116,  -408,  60,    -604,  -392,  548,   -840,  784,   -460,  656,  -544,
98
  -388,  -264,  908,   -800,  -628,  -612,  -568,  572,   -220,  164,  288,
99
  -16,   -308,  308,   -112,  -636,  -760,  280,   -668,  432,   364,  240,
100
  -196,  604,   340,   384,   196,   592,   -44,   -500,  432,   -580, -132,
101
  636,   -76,   392,   4,     -412,  540,   508,   328,   -356,  -36,  16,
102
  -220,  -64,   -248,  -60,   24,    -192,  368,   1040,  92,    -24,  -1044,
103
  -32,   40,    104,   148,   192,   -136,  -520,  56,    -816,  -224, 732,
104
  392,   356,   212,   -80,   -424,  -1008, -324,  588,   -1496, 576,  460,
105
  -816,  -848,  56,    -580,  -92,   -1372, -112,  -496,  200,   364,  52,
106
  -140,  48,    -48,   -60,   84,    72,    40,    132,   -356,  -268, -104,
107
  -284,  -404,  732,   -520,  164,   -304,  -540,  120,   328,   -76,  -460,
108
  756,   388,   588,   236,   -436,  -72,   -176,  -404,  -316,  -148, 716,
109
  -604,  404,   -72,   -88,   -888,  -68,   944,   88,    -220,  -344, 960,
110
  472,   460,   -232,  704,   120,   832,   -228,  692,   -508,  132,  -476,
111
  844,   -748,  -364,  -44,   1116,  -1104, -1056, 76,    428,   552,  -692,
112
  60,    356,   96,    -384,  -188,  -612,  -576,  736,   508,   892,  352,
113
  -1132, 504,   -24,   -352,  324,   332,   -600,  -312,  292,   508,  -144,
114
  -8,    484,   48,    284,   -260,  -240,  256,   -100,  -292,  -204, -44,
115
  472,   -204,  908,   -188,  -1000, -256,  92,    1164,  -392,  564,  356,
116
  652,   -28,   -884,  256,   484,   -192,  760,   -176,  376,   -524, -452,
117
  -436,  860,   -736,  212,   124,   504,   -476,  468,   76,    -472, 552,
118
  -692,  -944,  -620,  740,   -240,  400,   132,   20,    192,   -196, 264,
119
  -668,  -1012, -60,   296,   -316,  -828,  76,    -156,  284,   -768, -448,
120
  -832,  148,   248,   652,   616,   1236,  288,   -328,  -400,  -124, 588,
121
  220,   520,   -696,  1032,  768,   -740,  -92,   -272,  296,   448,  -464,
122
  412,   -200,  392,   440,   -200,  264,   -152,  -260,  320,   1032, 216,
123
  320,   -8,    -64,   156,   -1016, 1084,  1172,  536,   484,   -432, 132,
124
  372,   -52,   -256,  84,    116,   -352,  48,    116,   304,   -384, 412,
125
  924,   -300,  528,   628,   180,   648,   44,    -980,  -220,  1320, 48,
126
  332,   748,   524,   -268,  -720,  540,   -276,  564,   -344,  -208, -196,
127
  436,   896,   88,    -392,  132,   80,    -964,  -288,  568,   56,   -48,
128
  -456,  888,   8,     552,   -156,  -292,  948,   288,   128,   -716, -292,
129
  1192,  -152,  876,   352,   -600,  -260,  -812,  -468,  -28,   -120, -32,
130
  -44,   1284,  496,   192,   464,   312,   -76,   -516,  -380,  -456, -1012,
131
  -48,   308,   -156,  36,    492,   -156,  -808,  188,   1652,  68,   -120,
132
  -116,  316,   160,   -140,  352,   808,   -416,  592,   316,   -480, 56,
133
  528,   -204,  -568,  372,   -232,  752,   -344,  744,   -4,    324,  -416,
134
  -600,  768,   268,   -248,  -88,   -132,  -420,  -432,  80,    -288, 404,
135
  -316,  -1216, -588,  520,   -108,  92,    -320,  368,   -480,  -216, -92,
136
  1688,  -300,  180,   1020,  -176,  820,   -68,   -228,  -260,  436,  -904,
137
  20,    40,    -508,  440,   -736,  312,   332,   204,   760,   -372, 728,
138
  96,    -20,   -632,  -520,  -560,  336,   1076,  -64,   -532,  776,  584,
139
  192,   396,   -728,  -520,  276,   -188,  80,    -52,   -612,  -252, -48,
140
  648,   212,   -688,  228,   -52,   -260,  428,   -412,  -272,  -404, 180,
141
  816,   -796,  48,    152,   484,   -88,   -216,  988,   696,   188,  -528,
142
  648,   -116,  -180,  316,   476,   12,    -564,  96,    476,   -252, -364,
143
  -376,  -392,  556,   -256,  -576,  260,   -352,  120,   -16,   -136, -260,
144
  -492,  72,    556,   660,   580,   616,   772,   436,   424,   -32,  -324,
145
  -1268, 416,   -324,  -80,   920,   160,   228,   724,   32,    -516, 64,
146
  384,   68,    -128,  136,   240,   248,   -204,  -68,   252,   -932, -120,
147
  -480,  -628,  -84,   192,   852,   -404,  -288,  -132,  204,   100,  168,
148
  -68,   -196,  -868,  460,   1080,  380,   -80,   244,   0,     484,  -888,
149
  64,    184,   352,   600,   460,   164,   604,   -196,  320,   -64,  588,
150
  -184,  228,   12,    372,   48,    -848,  -344,  224,   208,   -200, 484,
151
  128,   -20,   272,   -468,  -840,  384,   256,   -720,  -520,  -464, -580,
152
  112,   -120,  644,   -356,  -208,  -608,  -528,  704,   560,   -424, 392,
153
  828,   40,    84,    200,   -152,  0,     -144,  584,   280,   -120, 80,
154
  -556,  -972,  -196,  -472,  724,   80,    168,   -32,   88,    160,  -688,
155
  0,     160,   356,   372,   -776,  740,   -128,  676,   -248,  -480, 4,
156
  -364,  96,    544,   232,   -1032, 956,   236,   356,   20,    -40,  300,
157
  24,    -676,  -596,  132,   1120,  -104,  532,   -1096, 568,   648,  444,
158
  508,   380,   188,   -376,  -604,  1488,  424,   24,    756,   -220, -192,
159
  716,   120,   920,   688,   168,   44,    -460,  568,   284,   1144, 1160,
160
  600,   424,   888,   656,   -356,  -320,  220,   316,   -176,  -724, -188,
161
  -816,  -628,  -348,  -228,  -380,  1012,  -452,  -660,  736,   928,  404,
162
  -696,  -72,   -268,  -892,  128,   184,   -344,  -780,  360,   336,  400,
163
  344,   428,   548,   -112,  136,   -228,  -216,  -820,  -516,  340,  92,
164
  -136,  116,   -300,  376,   -244,  100,   -316,  -520,  -284,  -12,  824,
165
  164,   -548,  -180,  -128,  116,   -924,  -828,  268,   -368,  -580, 620,
166
  192,   160,   0,     -1676, 1068,  424,   -56,   -360,  468,   -156, 720,
167
  288,   -528,  556,   -364,  548,   -148,  504,   316,   152,   -648, -620,
168
  -684,  -24,   -376,  -384,  -108,  -920,  -1032, 768,   180,   -264, -508,
169
  -1268, -260,  -60,   300,   -240,  988,   724,   -376,  -576,  -212, -736,
170
  556,   192,   1092,  -620,  -880,  376,   -56,   -4,    -216,  -32,  836,
171
  268,   396,   1332,  864,   -600,  100,   56,    -412,  -92,   356,  180,
172
  884,   -468,  -436,  292,   -388,  -804,  -704,  -840,  368,   -348, 140,
173
  -724,  1536,  940,   372,   112,   -372,  436,   -480,  1136,  296,  -32,
174
  -228,  132,   -48,   -220,  868,   -1016, -60,   -1044, -464,  328,  916,
175
  244,   12,    -736,  -296,  360,   468,   -376,  -108,  -92,   788,  368,
176
  -56,   544,   400,   -672,  -420,  728,   16,    320,   44,    -284, -380,
177
  -796,  488,   132,   204,   -596,  -372,  88,    -152,  -908,  -636, -572,
178
  -624,  -116,  -692,  -200,  -56,   276,   -88,   484,   -324,  948,  864,
179
  1000,  -456,  -184,  -276,  292,   -296,  156,   676,   320,   160,  908,
180
  -84,   -1236, -288,  -116,  260,   -372,  -644,  732,   -756,  -96,  84,
181
  344,   -520,  348,   -688,  240,   -84,   216,   -1044, -136,  -676, -396,
182
  -1500, 960,   -40,   176,   168,   1516,  420,   -504,  -344,  -364, -360,
183
  1216,  -940,  -380,  -212,  252,   -660,  -708,  484,   -444,  -152, 928,
184
  -120,  1112,  476,   -260,  560,   -148,  -344,  108,   -196,  228,  -288,
185
  504,   560,   -328,  -88,   288,   -1008, 460,   -228,  468,   -836, -196,
186
  76,    388,   232,   412,   -1168, -716,  -644,  756,   -172,  -356, -504,
187
  116,   432,   528,   48,    476,   -168,  -608,  448,   160,   -532, -272,
188
  28,    -676,  -12,   828,   980,   456,   520,   104,   -104,  256,  -344,
189
  -4,    -28,   -368,  -52,   -524,  -572,  -556,  -200,  768,   1124, -208,
190
  -512,  176,   232,   248,   -148,  -888,  604,   -600,  -304,  804,  -156,
191
  -212,  488,   -192,  -804,  -256,  368,   -360,  -916,  -328,  228,  -240,
192
  -448,  -472,  856,   -556,  -364,  572,   -12,   -156,  -368,  -340, 432,
193
  252,   -752,  -152,  288,   268,   -580,  -848,  -592,  108,   -76,  244,
194
  312,   -716,  592,   -80,   436,   360,   4,     -248,  160,   516,  584,
195
  732,   44,    -468,  -280,  -292,  -156,  -588,  28,    308,   912,  24,
196
  124,   156,   180,   -252,  944,   -924,  -772,  -520,  -428,  -624, 300,
197
  -212,  -1144, 32,    -724,  800,   -1128, -212,  -1288, -848,  180,  -416,
198
  440,   192,   -576,  -792,  -76,   -1080, 80,    -532,  -352,  -132, 380,
199
  -820,  148,   1112,  128,   164,   456,   700,   -924,  144,   -668, -384,
200
  648,   -832,  508,   552,   -52,   -100,  -656,  208,   -568,  748,  -88,
201
  680,   232,   300,   192,   -408,  -1012, -152,  -252,  -268,  272,  -876,
202
  -664,  -648,  -332,  -136,  16,    12,    1152,  -28,   332,   -536, 320,
203
  -672,  -460,  -316,  532,   -260,  228,   -40,   1052,  -816,  180,  88,
204
  -496,  -556,  -672,  -368,  428,   92,    356,   404,   -408,  252,  196,
205
  -176,  -556,  792,   268,   32,    372,   40,    96,    -332,  328,  120,
206
  372,   -900,  -40,   472,   -264,  -592,  952,   128,   656,   112,  664,
207
  -232,  420,   4,     -344,  -464,  556,   244,   -416,  -32,   252,  0,
208
  -412,  188,   -696,  508,   -476,  324,   -1096, 656,   -312,  560,  264,
209
  -136,  304,   160,   -64,   -580,  248,   336,   -720,  560,   -348, -288,
210
  -276,  -196,  -500,  852,   -544,  -236,  -1128, -992,  -776,  116,  56,
211
  52,    860,   884,   212,   -12,   168,   1020,  512,   -552,  924,  -148,
212
  716,   188,   164,   -340,  -520,  -184,  880,   -152,  -680,  -208, -1156,
213
  -300,  -528,  -472,  364,   100,   -744,  -1056, -32,   540,   280,  144,
214
  -676,  -32,   -232,  -280,  -224,  96,    568,   -76,   172,   148,  148,
215
  104,   32,    -296,  -32,   788,   -80,   32,    -16,   280,   288,  944,
216
  428,   -484
217
};
218
219
static const int gauss_bits = 11;
220
221
static int luma_subblock_size_y = 32;
222
static int luma_subblock_size_x = 32;
223
224
static int chroma_subblock_size_y = 16;
225
static int chroma_subblock_size_x = 16;
226
227
static const int min_luma_legal_range = 16;
228
static const int max_luma_legal_range = 235;
229
230
static const int min_chroma_legal_range = 16;
231
static const int max_chroma_legal_range = 240;
232
233
static int scaling_lut_y[256];
234
static int scaling_lut_cb[256];
235
static int scaling_lut_cr[256];
236
237
static int grain_min;
238
static int grain_max;
239
240
static uint16_t random_register = 0;  // random number generator register
241
242
static void dealloc_arrays(const aom_film_grain_t *params, int ***pred_pos_luma,
243
                           int ***pred_pos_chroma, int **luma_grain_block,
244
                           int **cb_grain_block, int **cr_grain_block,
245
                           int **y_line_buf, int **cb_line_buf,
246
                           int **cr_line_buf, int **y_col_buf, int **cb_col_buf,
247
14.6k
                           int **cr_col_buf) {
248
14.6k
  int num_pos_luma = 2 * params->ar_coeff_lag * (params->ar_coeff_lag + 1);
249
14.6k
  int num_pos_chroma = num_pos_luma;
250
14.6k
  if (params->num_y_points > 0) ++num_pos_chroma;
251
252
14.6k
  if (*pred_pos_luma) {
253
44.1k
    for (int row = 0; row < num_pos_luma; row++) {
254
29.4k
      aom_free((*pred_pos_luma)[row]);
255
29.4k
    }
256
14.6k
    aom_free(*pred_pos_luma);
257
14.6k
    *pred_pos_luma = NULL;
258
14.6k
  }
259
260
14.6k
  if (*pred_pos_chroma) {
261
56.2k
    for (int row = 0; row < num_pos_chroma; row++) {
262
41.6k
      aom_free((*pred_pos_chroma)[row]);
263
41.6k
    }
264
14.6k
    aom_free(*pred_pos_chroma);
265
14.6k
    *pred_pos_chroma = NULL;
266
14.6k
  }
267
268
14.6k
  aom_free(*y_line_buf);
269
14.6k
  *y_line_buf = NULL;
270
271
14.6k
  aom_free(*cb_line_buf);
272
14.6k
  *cb_line_buf = NULL;
273
274
14.6k
  aom_free(*cr_line_buf);
275
14.6k
  *cr_line_buf = NULL;
276
277
14.6k
  aom_free(*y_col_buf);
278
14.6k
  *y_col_buf = NULL;
279
280
14.6k
  aom_free(*cb_col_buf);
281
14.6k
  *cb_col_buf = NULL;
282
283
14.6k
  aom_free(*cr_col_buf);
284
14.6k
  *cr_col_buf = NULL;
285
286
14.6k
  aom_free(*luma_grain_block);
287
14.6k
  *luma_grain_block = NULL;
288
289
14.6k
  aom_free(*cb_grain_block);
290
14.6k
  *cb_grain_block = NULL;
291
292
14.6k
  aom_free(*cr_grain_block);
293
14.6k
  *cr_grain_block = NULL;
294
14.6k
}
295
296
static bool init_arrays(const aom_film_grain_t *params, int luma_stride,
297
                        int chroma_stride, int ***pred_pos_luma_p,
298
                        int ***pred_pos_chroma_p, int **luma_grain_block,
299
                        int **cb_grain_block, int **cr_grain_block,
300
                        int **y_line_buf, int **cb_line_buf, int **cr_line_buf,
301
                        int **y_col_buf, int **cb_col_buf, int **cr_col_buf,
302
                        int luma_grain_samples, int chroma_grain_samples,
303
14.6k
                        int chroma_subsamp_y, int chroma_subsamp_x) {
304
14.6k
  *pred_pos_luma_p = NULL;
305
14.6k
  *pred_pos_chroma_p = NULL;
306
14.6k
  *luma_grain_block = NULL;
307
14.6k
  *cb_grain_block = NULL;
308
14.6k
  *cr_grain_block = NULL;
309
14.6k
  *y_line_buf = NULL;
310
14.6k
  *cb_line_buf = NULL;
311
14.6k
  *cr_line_buf = NULL;
312
14.6k
  *y_col_buf = NULL;
313
14.6k
  *cb_col_buf = NULL;
314
14.6k
  *cr_col_buf = NULL;
315
316
14.6k
  memset(scaling_lut_y, 0, sizeof(*scaling_lut_y) * 256);
317
14.6k
  memset(scaling_lut_cb, 0, sizeof(*scaling_lut_cb) * 256);
318
14.6k
  memset(scaling_lut_cr, 0, sizeof(*scaling_lut_cr) * 256);
319
320
14.6k
  int num_pos_luma = 2 * params->ar_coeff_lag * (params->ar_coeff_lag + 1);
321
14.6k
  int num_pos_chroma = num_pos_luma;
322
14.6k
  if (params->num_y_points > 0) ++num_pos_chroma;
323
324
14.6k
  int **pred_pos_luma;
325
14.6k
  int **pred_pos_chroma;
326
327
14.6k
  pred_pos_luma = (int **)aom_calloc(num_pos_luma, sizeof(*pred_pos_luma));
328
14.6k
  if (!pred_pos_luma) return false;
329
330
44.1k
  for (int row = 0; row < num_pos_luma; row++) {
331
29.4k
    pred_pos_luma[row] = (int *)aom_malloc(sizeof(**pred_pos_luma) * 3);
332
29.4k
    if (!pred_pos_luma[row]) {
333
0
      dealloc_arrays(params, pred_pos_luma_p, pred_pos_chroma_p,
334
0
                     luma_grain_block, cb_grain_block, cr_grain_block,
335
0
                     y_line_buf, cb_line_buf, cr_line_buf, y_col_buf,
336
0
                     cb_col_buf, cr_col_buf);
337
0
      return false;
338
0
    }
339
29.4k
  }
340
341
14.6k
  pred_pos_chroma =
342
14.6k
      (int **)aom_calloc(num_pos_chroma, sizeof(*pred_pos_chroma));
343
14.6k
  if (!pred_pos_chroma) {
344
0
    dealloc_arrays(params, pred_pos_luma_p, pred_pos_chroma_p, luma_grain_block,
345
0
                   cb_grain_block, cr_grain_block, y_line_buf, cb_line_buf,
346
0
                   cr_line_buf, y_col_buf, cb_col_buf, cr_col_buf);
347
0
    return false;
348
0
  }
349
350
56.2k
  for (int row = 0; row < num_pos_chroma; row++) {
351
41.6k
    pred_pos_chroma[row] = (int *)aom_malloc(sizeof(**pred_pos_chroma) * 3);
352
41.6k
    if (!pred_pos_chroma[row]) {
353
0
      dealloc_arrays(params, pred_pos_luma_p, pred_pos_chroma_p,
354
0
                     luma_grain_block, cb_grain_block, cr_grain_block,
355
0
                     y_line_buf, cb_line_buf, cr_line_buf, y_col_buf,
356
0
                     cb_col_buf, cr_col_buf);
357
0
      return false;
358
0
    }
359
41.6k
  }
360
361
14.6k
  int pos_ar_index = 0;
362
363
21.5k
  for (int row = -params->ar_coeff_lag; row < 0; row++) {
364
29.4k
    for (int col = -params->ar_coeff_lag; col < params->ar_coeff_lag + 1;
365
22.5k
         col++) {
366
22.5k
      pred_pos_luma[pos_ar_index][0] = row;
367
22.5k
      pred_pos_luma[pos_ar_index][1] = col;
368
22.5k
      pred_pos_luma[pos_ar_index][2] = 0;
369
370
22.5k
      pred_pos_chroma[pos_ar_index][0] = row;
371
22.5k
      pred_pos_chroma[pos_ar_index][1] = col;
372
22.5k
      pred_pos_chroma[pos_ar_index][2] = 0;
373
22.5k
      ++pos_ar_index;
374
22.5k
    }
375
6.92k
  }
376
377
21.5k
  for (int col = -params->ar_coeff_lag; col < 0; col++) {
378
6.92k
    pred_pos_luma[pos_ar_index][0] = 0;
379
6.92k
    pred_pos_luma[pos_ar_index][1] = col;
380
6.92k
    pred_pos_luma[pos_ar_index][2] = 0;
381
382
6.92k
    pred_pos_chroma[pos_ar_index][0] = 0;
383
6.92k
    pred_pos_chroma[pos_ar_index][1] = col;
384
6.92k
    pred_pos_chroma[pos_ar_index][2] = 0;
385
386
6.92k
    ++pos_ar_index;
387
6.92k
  }
388
389
14.6k
  if (params->num_y_points > 0) {
390
12.1k
    pred_pos_chroma[pos_ar_index][0] = 0;
391
12.1k
    pred_pos_chroma[pos_ar_index][1] = 0;
392
12.1k
    pred_pos_chroma[pos_ar_index][2] = 1;
393
12.1k
  }
394
395
14.6k
  *pred_pos_luma_p = pred_pos_luma;
396
14.6k
  *pred_pos_chroma_p = pred_pos_chroma;
397
398
14.6k
  *y_line_buf = (int *)aom_malloc(sizeof(**y_line_buf) * luma_stride * 2);
399
14.6k
  *cb_line_buf = (int *)aom_malloc(sizeof(**cb_line_buf) * chroma_stride *
400
14.6k
                                   (2 >> chroma_subsamp_y));
401
14.6k
  *cr_line_buf = (int *)aom_malloc(sizeof(**cr_line_buf) * chroma_stride *
402
14.6k
                                   (2 >> chroma_subsamp_y));
403
404
14.6k
  *y_col_buf =
405
14.6k
      (int *)aom_malloc(sizeof(**y_col_buf) * (luma_subblock_size_y + 2) * 2);
406
14.6k
  *cb_col_buf =
407
14.6k
      (int *)aom_malloc(sizeof(**cb_col_buf) *
408
14.6k
                        (chroma_subblock_size_y + (2 >> chroma_subsamp_y)) *
409
14.6k
                        (2 >> chroma_subsamp_x));
410
14.6k
  *cr_col_buf =
411
14.6k
      (int *)aom_malloc(sizeof(**cr_col_buf) *
412
14.6k
                        (chroma_subblock_size_y + (2 >> chroma_subsamp_y)) *
413
14.6k
                        (2 >> chroma_subsamp_x));
414
415
14.6k
  *luma_grain_block =
416
14.6k
      (int *)aom_malloc(sizeof(**luma_grain_block) * luma_grain_samples);
417
14.6k
  *cb_grain_block =
418
14.6k
      (int *)aom_malloc(sizeof(**cb_grain_block) * chroma_grain_samples);
419
14.6k
  *cr_grain_block =
420
14.6k
      (int *)aom_malloc(sizeof(**cr_grain_block) * chroma_grain_samples);
421
14.6k
  if (!(*pred_pos_luma_p && *pred_pos_chroma_p && *y_line_buf && *cb_line_buf &&
422
14.6k
        *cr_line_buf && *y_col_buf && *cb_col_buf && *cr_col_buf &&
423
14.6k
        *luma_grain_block && *cb_grain_block && *cr_grain_block)) {
424
0
    dealloc_arrays(params, pred_pos_luma_p, pred_pos_chroma_p, luma_grain_block,
425
0
                   cb_grain_block, cr_grain_block, y_line_buf, cb_line_buf,
426
0
                   cr_line_buf, y_col_buf, cb_col_buf, cr_col_buf);
427
0
    return false;
428
0
  }
429
14.6k
  return true;
430
14.6k
}
431
432
// get a number between 0 and 2^bits - 1
433
136M
static inline int get_random_number(int bits) {
434
136M
  uint16_t bit;
435
136M
  bit = ((random_register >> 0) ^ (random_register >> 1) ^
436
136M
         (random_register >> 3) ^ (random_register >> 12)) &
437
136M
        1;
438
136M
  random_register = (random_register >> 1) | (bit << 15);
439
136M
  return (random_register >> (16 - bits)) & ((1 << bits) - 1);
440
136M
}
441
442
45.0k
static void init_random_generator(int luma_line, uint16_t seed) {
443
  // same for the picture
444
445
45.0k
  uint16_t msb = (seed >> 8) & 255;
446
45.0k
  uint16_t lsb = seed & 255;
447
448
45.0k
  random_register = (msb << 8) + lsb;
449
450
  //  changes for each row
451
45.0k
  int luma_num = luma_line >> 5;
452
453
45.0k
  random_register ^= ((luma_num * 37 + 178) & 255) << 8;
454
45.0k
  random_register ^= ((luma_num * 173 + 105) & 255);
455
45.0k
}
456
457
static void generate_luma_grain_block(
458
    const aom_film_grain_t *params, int **pred_pos_luma, int *luma_grain_block,
459
    int luma_block_size_y, int luma_block_size_x, int luma_grain_stride,
460
14.6k
    int left_pad, int top_pad, int right_pad, int bottom_pad) {
461
14.6k
  if (params->num_y_points == 0) {
462
2.46k
    memset(luma_grain_block, 0,
463
2.46k
           sizeof(*luma_grain_block) * luma_block_size_y * luma_grain_stride);
464
2.46k
    return;
465
2.46k
  }
466
467
12.1k
  int bit_depth = params->bit_depth;
468
12.1k
  int gauss_sec_shift = 12 - bit_depth + params->grain_scale_shift;
469
470
12.1k
  int num_pos_luma = 2 * params->ar_coeff_lag * (params->ar_coeff_lag + 1);
471
12.1k
  int rounding_offset = (1 << (params->ar_coeff_shift - 1));
472
473
900k
  for (int i = 0; i < luma_block_size_y; i++)
474
73.7M
    for (int j = 0; j < luma_block_size_x; j++)
475
72.8M
      luma_grain_block[i * luma_grain_stride + j] =
476
72.8M
          (gaussian_sequence[get_random_number(gauss_bits)] +
477
72.8M
           ((1 << gauss_sec_shift) >> 1)) >>
478
72.8M
          gauss_sec_shift;
479
480
864k
  for (int i = top_pad; i < luma_block_size_y - bottom_pad; i++)
481
65.5M
    for (int j = left_pad; j < luma_block_size_x - right_pad; j++) {
482
64.7M
      int wsum = 0;
483
199M
      for (int pos = 0; pos < num_pos_luma; pos++) {
484
134M
        wsum = wsum + params->ar_coeffs_y[pos] *
485
134M
                          luma_grain_block[(i + pred_pos_luma[pos][0]) *
486
134M
                                               luma_grain_stride +
487
134M
                                           j + pred_pos_luma[pos][1]];
488
134M
      }
489
64.7M
      luma_grain_block[i * luma_grain_stride + j] =
490
64.7M
          clamp(luma_grain_block[i * luma_grain_stride + j] +
491
64.7M
                    ((wsum + rounding_offset) >> params->ar_coeff_shift),
492
64.7M
                grain_min, grain_max);
493
64.7M
    }
494
12.1k
}
495
496
static bool generate_chroma_grain_blocks(
497
    const aom_film_grain_t *params, int **pred_pos_chroma,
498
    int *luma_grain_block, int *cb_grain_block, int *cr_grain_block,
499
    int luma_grain_stride, int chroma_block_size_y, int chroma_block_size_x,
500
    int chroma_grain_stride, int left_pad, int top_pad, int right_pad,
501
14.6k
    int bottom_pad, int chroma_subsamp_y, int chroma_subsamp_x) {
502
14.6k
  int bit_depth = params->bit_depth;
503
14.6k
  int gauss_sec_shift = 12 - bit_depth + params->grain_scale_shift;
504
505
14.6k
  int num_pos_chroma = 2 * params->ar_coeff_lag * (params->ar_coeff_lag + 1);
506
14.6k
  if (params->num_y_points > 0) ++num_pos_chroma;
507
14.6k
  int rounding_offset = (1 << (params->ar_coeff_shift - 1));
508
14.6k
  int chroma_grain_block_size = chroma_block_size_y * chroma_grain_stride;
509
510
14.6k
  if (params->num_cb_points || params->chroma_scaling_from_luma) {
511
9.99k
    init_random_generator(7 << 5, params->random_seed);
512
513
501k
    for (int i = 0; i < chroma_block_size_y; i++)
514
24.6M
      for (int j = 0; j < chroma_block_size_x; j++)
515
24.1M
        cb_grain_block[i * chroma_grain_stride + j] =
516
24.1M
            (gaussian_sequence[get_random_number(gauss_bits)] +
517
24.1M
             ((1 << gauss_sec_shift) >> 1)) >>
518
24.1M
            gauss_sec_shift;
519
9.99k
  } else {
520
4.63k
    memset(cb_grain_block, 0,
521
4.63k
           sizeof(*cb_grain_block) * chroma_grain_block_size);
522
4.63k
  }
523
524
14.6k
  if (params->num_cr_points || params->chroma_scaling_from_luma) {
525
12.5k
    init_random_generator(11 << 5, params->random_seed);
526
527
687k
    for (int i = 0; i < chroma_block_size_y; i++)
528
40.1M
      for (int j = 0; j < chroma_block_size_x; j++)
529
39.4M
        cr_grain_block[i * chroma_grain_stride + j] =
530
39.4M
            (gaussian_sequence[get_random_number(gauss_bits)] +
531
39.4M
             ((1 << gauss_sec_shift) >> 1)) >>
532
39.4M
            gauss_sec_shift;
533
12.5k
  } else {
534
2.11k
    memset(cr_grain_block, 0,
535
2.11k
           sizeof(*cr_grain_block) * chroma_grain_block_size);
536
2.11k
  }
537
538
789k
  for (int i = top_pad; i < chroma_block_size_y - bottom_pad; i++)
539
43.9M
    for (int j = left_pad; j < chroma_block_size_x - right_pad; j++) {
540
43.1M
      int wsum_cb = 0;
541
43.1M
      int wsum_cr = 0;
542
127M
      for (int pos = 0; pos < num_pos_chroma; pos++) {
543
83.9M
        if (pred_pos_chroma[pos][2] == 0) {
544
46.9M
          wsum_cb = wsum_cb + params->ar_coeffs_cb[pos] *
545
46.9M
                                  cb_grain_block[(i + pred_pos_chroma[pos][0]) *
546
46.9M
                                                     chroma_grain_stride +
547
46.9M
                                                 j + pred_pos_chroma[pos][1]];
548
46.9M
          wsum_cr = wsum_cr + params->ar_coeffs_cr[pos] *
549
46.9M
                                  cr_grain_block[(i + pred_pos_chroma[pos][0]) *
550
46.9M
                                                     chroma_grain_stride +
551
46.9M
                                                 j + pred_pos_chroma[pos][1]];
552
46.9M
        } else if (pred_pos_chroma[pos][2] == 1) {
553
36.9M
          int av_luma = 0;
554
36.9M
          int luma_coord_y = ((i - top_pad) << chroma_subsamp_y) + top_pad;
555
36.9M
          int luma_coord_x = ((j - left_pad) << chroma_subsamp_x) + left_pad;
556
557
83.0M
          for (int k = luma_coord_y; k < luma_coord_y + chroma_subsamp_y + 1;
558
46.0M
               k++)
559
110M
            for (int l = luma_coord_x; l < luma_coord_x + chroma_subsamp_x + 1;
560
64.7M
                 l++)
561
64.7M
              av_luma += luma_grain_block[k * luma_grain_stride + l];
562
563
36.9M
          av_luma =
564
36.9M
              (av_luma + ((1 << (chroma_subsamp_y + chroma_subsamp_x)) >> 1)) >>
565
36.9M
              (chroma_subsamp_y + chroma_subsamp_x);
566
567
36.9M
          wsum_cb = wsum_cb + params->ar_coeffs_cb[pos] * av_luma;
568
36.9M
          wsum_cr = wsum_cr + params->ar_coeffs_cr[pos] * av_luma;
569
36.9M
        } else {
570
0
          fprintf(
571
0
              stderr,
572
0
              "Grain synthesis: prediction between two chroma components is "
573
0
              "not supported!");
574
0
          return false;
575
0
        }
576
83.9M
      }
577
43.1M
      if (params->num_cb_points || params->chroma_scaling_from_luma)
578
19.9M
        cb_grain_block[i * chroma_grain_stride + j] =
579
19.9M
            clamp(cb_grain_block[i * chroma_grain_stride + j] +
580
19.9M
                      ((wsum_cb + rounding_offset) >> params->ar_coeff_shift),
581
19.9M
                  grain_min, grain_max);
582
43.1M
      if (params->num_cr_points || params->chroma_scaling_from_luma)
583
33.5M
        cr_grain_block[i * chroma_grain_stride + j] =
584
33.5M
            clamp(cr_grain_block[i * chroma_grain_stride + j] +
585
33.5M
                      ((wsum_cr + rounding_offset) >> params->ar_coeff_shift),
586
33.5M
                  grain_min, grain_max);
587
43.1M
    }
588
14.6k
  return true;
589
14.6k
}
590
591
static void init_scaling_function(const int scaling_points[][2], int num_points,
592
27.2k
                                  int scaling_lut[]) {
593
27.2k
  if (num_points == 0) return;
594
595
579k
  for (int i = 0; i < scaling_points[0][0]; i++)
596
561k
    scaling_lut[i] = scaling_points[0][1];
597
598
40.6k
  for (int point = 0; point < num_points - 1; point++) {
599
22.6k
    int delta_y = scaling_points[point + 1][1] - scaling_points[point][1];
600
22.6k
    int delta_x = scaling_points[point + 1][0] - scaling_points[point][0];
601
602
22.6k
    int64_t delta = delta_y * ((65536 + (delta_x >> 1)) / delta_x);
603
604
2.59M
    for (int x = 0; x < delta_x; x++) {
605
2.57M
      scaling_lut[scaling_points[point][0] + x] =
606
2.57M
          scaling_points[point][1] + (int)((x * delta + 32768) >> 16);
607
2.57M
    }
608
22.6k
  }
609
610
1.49M
  for (int i = scaling_points[num_points - 1][0]; i < 256; i++)
611
1.47M
    scaling_lut[i] = scaling_points[num_points - 1][1];
612
17.9k
}
613
614
// function that extracts samples from a LUT (and interpolates intemediate
615
// frames for 10- and 12-bit video)
616
36.8M
static int scale_LUT(int *scaling_lut, int index, int bit_depth) {
617
36.8M
  int x = index >> (bit_depth - 8);
618
619
36.8M
  if (!(bit_depth - 8) || x == 255)
620
5.35M
    return scaling_lut[x];
621
31.4M
  else
622
31.4M
    return scaling_lut[x] + (((scaling_lut[x + 1] - scaling_lut[x]) *
623
31.4M
                                  (index & ((1 << (bit_depth - 8)) - 1)) +
624
31.4M
                              (1 << (bit_depth - 9))) >>
625
31.4M
                             (bit_depth - 8));
626
36.8M
}
627
628
static void add_noise_to_block(const aom_film_grain_t *params, uint8_t *luma,
629
                               uint8_t *cb, uint8_t *cr, int luma_stride,
630
                               int chroma_stride, int *luma_grain,
631
                               int *cb_grain, int *cr_grain,
632
                               int luma_grain_stride, int chroma_grain_stride,
633
                               int half_luma_height, int half_luma_width,
634
                               int bit_depth, int chroma_subsamp_y,
635
23.7k
                               int chroma_subsamp_x, int mc_identity) {
636
23.7k
  int cb_mult = params->cb_mult - 128;            // fixed scale
637
23.7k
  int cb_luma_mult = params->cb_luma_mult - 128;  // fixed scale
638
23.7k
  int cb_offset = params->cb_offset - 256;
639
640
23.7k
  int cr_mult = params->cr_mult - 128;            // fixed scale
641
23.7k
  int cr_luma_mult = params->cr_luma_mult - 128;  // fixed scale
642
23.7k
  int cr_offset = params->cr_offset - 256;
643
644
23.7k
  int rounding_offset = (1 << (params->scaling_shift - 1));
645
646
23.7k
  int apply_y = params->num_y_points > 0 ? 1 : 0;
647
23.7k
  int apply_cb =
648
23.7k
      (params->num_cb_points > 0 || params->chroma_scaling_from_luma) ? 1 : 0;
649
23.7k
  int apply_cr =
650
23.7k
      (params->num_cr_points > 0 || params->chroma_scaling_from_luma) ? 1 : 0;
651
652
23.7k
  if (params->chroma_scaling_from_luma) {
653
6.40k
    cb_mult = 0;        // fixed scale
654
6.40k
    cb_luma_mult = 64;  // fixed scale
655
6.40k
    cb_offset = 0;
656
657
6.40k
    cr_mult = 0;        // fixed scale
658
6.40k
    cr_luma_mult = 64;  // fixed scale
659
6.40k
    cr_offset = 0;
660
6.40k
  }
661
662
23.7k
  int min_luma, max_luma, min_chroma, max_chroma;
663
664
23.7k
  if (params->clip_to_restricted_range) {
665
11.9k
    min_luma = min_luma_legal_range;
666
11.9k
    max_luma = max_luma_legal_range;
667
668
11.9k
    if (mc_identity) {
669
718
      min_chroma = min_luma_legal_range;
670
718
      max_chroma = max_luma_legal_range;
671
11.2k
    } else {
672
11.2k
      min_chroma = min_chroma_legal_range;
673
11.2k
      max_chroma = max_chroma_legal_range;
674
11.2k
    }
675
11.9k
  } else {
676
11.8k
    min_luma = min_chroma = 0;
677
11.8k
    max_luma = max_chroma = 255;
678
11.8k
  }
679
680
242k
  for (int i = 0; i < (half_luma_height << (1 - chroma_subsamp_y)); i++) {
681
2.85M
    for (int j = 0; j < (half_luma_width << (1 - chroma_subsamp_x)); j++) {
682
2.63M
      int average_luma = 0;
683
2.63M
      if (chroma_subsamp_x) {
684
1.61M
        average_luma = (luma[(i << chroma_subsamp_y) * luma_stride +
685
1.61M
                             (j << chroma_subsamp_x)] +
686
1.61M
                        luma[(i << chroma_subsamp_y) * luma_stride +
687
1.61M
                             (j << chroma_subsamp_x) + 1] +
688
1.61M
                        1) >>
689
1.61M
                       1;
690
1.61M
      } else {
691
1.02M
        average_luma = luma[(i << chroma_subsamp_y) * luma_stride + j];
692
1.02M
      }
693
694
2.63M
      if (apply_cb) {
695
603k
        cb[i * chroma_stride + j] = clamp(
696
603k
            cb[i * chroma_stride + j] +
697
603k
                ((scale_LUT(scaling_lut_cb,
698
603k
                            clamp(((average_luma * cb_luma_mult +
699
603k
                                    cb_mult * cb[i * chroma_stride + j]) >>
700
603k
                                   6) +
701
603k
                                      cb_offset,
702
603k
                                  0, (256 << (bit_depth - 8)) - 1),
703
603k
                            8) *
704
603k
                      cb_grain[i * chroma_grain_stride + j] +
705
603k
                  rounding_offset) >>
706
603k
                 params->scaling_shift),
707
603k
            min_chroma, max_chroma);
708
603k
      }
709
710
2.63M
      if (apply_cr) {
711
609k
        cr[i * chroma_stride + j] = clamp(
712
609k
            cr[i * chroma_stride + j] +
713
609k
                ((scale_LUT(scaling_lut_cr,
714
609k
                            clamp(((average_luma * cr_luma_mult +
715
609k
                                    cr_mult * cr[i * chroma_stride + j]) >>
716
609k
                                   6) +
717
609k
                                      cr_offset,
718
609k
                                  0, (256 << (bit_depth - 8)) - 1),
719
609k
                            8) *
720
609k
                      cr_grain[i * chroma_grain_stride + j] +
721
609k
                  rounding_offset) >>
722
609k
                 params->scaling_shift),
723
609k
            min_chroma, max_chroma);
724
609k
      }
725
2.63M
    }
726
218k
  }
727
728
23.7k
  if (apply_y) {
729
250k
    for (int i = 0; i < (half_luma_height << 1); i++) {
730
4.13M
      for (int j = 0; j < (half_luma_width << 1); j++) {
731
3.89M
        luma[i * luma_stride + j] =
732
3.89M
            clamp(luma[i * luma_stride + j] +
733
3.89M
                      ((scale_LUT(scaling_lut_y, luma[i * luma_stride + j], 8) *
734
3.89M
                            luma_grain[i * luma_grain_stride + j] +
735
3.89M
                        rounding_offset) >>
736
3.89M
                       params->scaling_shift),
737
3.89M
                  min_luma, max_luma);
738
3.89M
      }
739
233k
    }
740
16.8k
  }
741
23.7k
}
742
743
static void add_noise_to_block_hbd(
744
    const aom_film_grain_t *params, uint16_t *luma, uint16_t *cb, uint16_t *cr,
745
    int luma_stride, int chroma_stride, int *luma_grain, int *cb_grain,
746
    int *cr_grain, int luma_grain_stride, int chroma_grain_stride,
747
    int half_luma_height, int half_luma_width, int bit_depth,
748
69.2k
    int chroma_subsamp_y, int chroma_subsamp_x, int mc_identity) {
749
69.2k
  int cb_mult = params->cb_mult - 128;            // fixed scale
750
69.2k
  int cb_luma_mult = params->cb_luma_mult - 128;  // fixed scale
751
  // offset value depends on the bit depth
752
69.2k
  int cb_offset = (params->cb_offset << (bit_depth - 8)) - (1 << bit_depth);
753
754
69.2k
  int cr_mult = params->cr_mult - 128;            // fixed scale
755
69.2k
  int cr_luma_mult = params->cr_luma_mult - 128;  // fixed scale
756
  // offset value depends on the bit depth
757
69.2k
  int cr_offset = (params->cr_offset << (bit_depth - 8)) - (1 << bit_depth);
758
759
69.2k
  int rounding_offset = (1 << (params->scaling_shift - 1));
760
761
69.2k
  int apply_y = params->num_y_points > 0 ? 1 : 0;
762
69.2k
  int apply_cb =
763
69.2k
      (params->num_cb_points > 0 || params->chroma_scaling_from_luma) > 0 ? 1
764
69.2k
                                                                          : 0;
765
69.2k
  int apply_cr =
766
69.2k
      (params->num_cr_points > 0 || params->chroma_scaling_from_luma) > 0 ? 1
767
69.2k
                                                                          : 0;
768
769
69.2k
  if (params->chroma_scaling_from_luma) {
770
28.2k
    cb_mult = 0;        // fixed scale
771
28.2k
    cb_luma_mult = 64;  // fixed scale
772
28.2k
    cb_offset = 0;
773
774
28.2k
    cr_mult = 0;        // fixed scale
775
28.2k
    cr_luma_mult = 64;  // fixed scale
776
28.2k
    cr_offset = 0;
777
28.2k
  }
778
779
69.2k
  int min_luma, max_luma, min_chroma, max_chroma;
780
781
69.2k
  if (params->clip_to_restricted_range) {
782
11.5k
    min_luma = min_luma_legal_range << (bit_depth - 8);
783
11.5k
    max_luma = max_luma_legal_range << (bit_depth - 8);
784
785
11.5k
    if (mc_identity) {
786
763
      min_chroma = min_luma_legal_range << (bit_depth - 8);
787
763
      max_chroma = max_luma_legal_range << (bit_depth - 8);
788
10.7k
    } else {
789
10.7k
      min_chroma = min_chroma_legal_range << (bit_depth - 8);
790
10.7k
      max_chroma = max_chroma_legal_range << (bit_depth - 8);
791
10.7k
    }
792
57.7k
  } else {
793
57.7k
    min_luma = min_chroma = 0;
794
57.7k
    max_luma = max_chroma = (256 << (bit_depth - 8)) - 1;
795
57.7k
  }
796
797
960k
  for (int i = 0; i < (half_luma_height << (1 - chroma_subsamp_y)); i++) {
798
13.4M
    for (int j = 0; j < (half_luma_width << (1 - chroma_subsamp_x)); j++) {
799
12.5M
      int average_luma = 0;
800
12.5M
      if (chroma_subsamp_x) {
801
1.58M
        average_luma = (luma[(i << chroma_subsamp_y) * luma_stride +
802
1.58M
                             (j << chroma_subsamp_x)] +
803
1.58M
                        luma[(i << chroma_subsamp_y) * luma_stride +
804
1.58M
                             (j << chroma_subsamp_x) + 1] +
805
1.58M
                        1) >>
806
1.58M
                       1;
807
11.0M
      } else {
808
11.0M
        average_luma = luma[(i << chroma_subsamp_y) * luma_stride + j];
809
11.0M
      }
810
811
12.5M
      if (apply_cb) {
812
6.10M
        cb[i * chroma_stride + j] = clamp(
813
6.10M
            cb[i * chroma_stride + j] +
814
6.10M
                ((scale_LUT(scaling_lut_cb,
815
6.10M
                            clamp(((average_luma * cb_luma_mult +
816
6.10M
                                    cb_mult * cb[i * chroma_stride + j]) >>
817
6.10M
                                   6) +
818
6.10M
                                      cb_offset,
819
6.10M
                                  0, (256 << (bit_depth - 8)) - 1),
820
6.10M
                            bit_depth) *
821
6.10M
                      cb_grain[i * chroma_grain_stride + j] +
822
6.10M
                  rounding_offset) >>
823
6.10M
                 params->scaling_shift),
824
6.10M
            min_chroma, max_chroma);
825
6.10M
      }
826
12.5M
      if (apply_cr) {
827
10.2M
        cr[i * chroma_stride + j] = clamp(
828
10.2M
            cr[i * chroma_stride + j] +
829
10.2M
                ((scale_LUT(scaling_lut_cr,
830
10.2M
                            clamp(((average_luma * cr_luma_mult +
831
10.2M
                                    cr_mult * cr[i * chroma_stride + j]) >>
832
10.2M
                                   6) +
833
10.2M
                                      cr_offset,
834
10.2M
                                  0, (256 << (bit_depth - 8)) - 1),
835
10.2M
                            bit_depth) *
836
10.2M
                      cr_grain[i * chroma_grain_stride + j] +
837
10.2M
                  rounding_offset) >>
838
10.2M
                 params->scaling_shift),
839
10.2M
            min_chroma, max_chroma);
840
10.2M
      }
841
12.5M
    }
842
890k
  }
843
844
69.2k
  if (apply_y) {
845
1.04M
    for (int i = 0; i < (half_luma_height << 1); i++) {
846
16.3M
      for (int j = 0; j < (half_luma_width << 1); j++) {
847
15.3M
        luma[i * luma_stride + j] =
848
15.3M
            clamp(luma[i * luma_stride + j] +
849
15.3M
                      ((scale_LUT(scaling_lut_y, luma[i * luma_stride + j],
850
15.3M
                                  bit_depth) *
851
15.3M
                            luma_grain[i * luma_grain_stride + j] +
852
15.3M
                        rounding_offset) >>
853
15.3M
                       params->scaling_shift),
854
15.3M
                  min_luma, max_luma);
855
15.3M
      }
856
980k
    }
857
66.7k
  }
858
69.2k
}
859
860
static void copy_rect(uint8_t *src, int src_stride, uint8_t *dst,
861
                      int dst_stride, int width, int height,
862
43.8k
                      int use_high_bit_depth) {
863
43.8k
  int hbd_coeff = use_high_bit_depth ? 2 : 1;
864
939k
  while (height) {
865
895k
    memcpy(dst, src, width * sizeof(uint8_t) * hbd_coeff);
866
895k
    src += src_stride;
867
895k
    dst += dst_stride;
868
895k
    --height;
869
895k
  }
870
43.8k
  return;
871
43.8k
}
872
873
static void copy_area(int *src, int src_stride, int *dst, int dst_stride,
874
283k
                      int width, int height) {
875
2.66M
  while (height) {
876
2.37M
    memcpy(dst, src, width * sizeof(*src));
877
2.37M
    src += src_stride;
878
2.37M
    dst += dst_stride;
879
2.37M
    --height;
880
2.37M
  }
881
283k
  return;
882
283k
}
883
884
static void extend_even(uint8_t *dst, int dst_stride, int width, int height,
885
14.6k
                        int use_high_bit_depth) {
886
14.6k
  if ((width & 1) == 0 && (height & 1) == 0) return;
887
13.1k
  if (use_high_bit_depth) {
888
9.28k
    uint16_t *dst16 = (uint16_t *)dst;
889
9.28k
    int dst16_stride = dst_stride / 2;
890
9.28k
    if (width & 1) {
891
195k
      for (int i = 0; i < height; ++i)
892
186k
        dst16[i * dst16_stride + width] = dst16[i * dst16_stride + width - 1];
893
9.16k
    }
894
9.28k
    width = (width + 1) & (~1);
895
9.28k
    if (height & 1) {
896
153
      memcpy(&dst16[height * dst16_stride], &dst16[(height - 1) * dst16_stride],
897
153
             sizeof(*dst16) * width);
898
153
    }
899
9.28k
  } else {
900
3.87k
    if (width & 1) {
901
50.5k
      for (int i = 0; i < height; ++i)
902
48.8k
        dst[i * dst_stride + width] = dst[i * dst_stride + width - 1];
903
1.69k
    }
904
3.87k
    width = (width + 1) & (~1);
905
3.87k
    if (height & 1) {
906
2.45k
      memcpy(&dst[height * dst_stride], &dst[(height - 1) * dst_stride],
907
2.45k
             sizeof(*dst) * width);
908
2.45k
    }
909
3.87k
  }
910
13.1k
}
911
912
static void ver_boundary_overlap(int *left_block, int left_stride,
913
                                 int *right_block, int right_stride,
914
                                 int *dst_block, int dst_stride, int width,
915
62.3k
                                 int height) {
916
62.3k
  if (width == 1) {
917
178k
    while (height) {
918
161k
      *dst_block = clamp((*left_block * 23 + *right_block * 22 + 16) >> 5,
919
161k
                         grain_min, grain_max);
920
161k
      left_block += left_stride;
921
161k
      right_block += right_stride;
922
161k
      dst_block += dst_stride;
923
161k
      --height;
924
161k
    }
925
16.4k
    return;
926
45.8k
  } else if (width == 2) {
927
1.12M
    while (height) {
928
1.08M
      dst_block[0] = clamp((27 * left_block[0] + 17 * right_block[0] + 16) >> 5,
929
1.08M
                           grain_min, grain_max);
930
1.08M
      dst_block[1] = clamp((17 * left_block[1] + 27 * right_block[1] + 16) >> 5,
931
1.08M
                           grain_min, grain_max);
932
1.08M
      left_block += left_stride;
933
1.08M
      right_block += right_stride;
934
1.08M
      dst_block += dst_stride;
935
1.08M
      --height;
936
1.08M
    }
937
45.8k
    return;
938
45.8k
  }
939
62.3k
}
940
941
static void hor_boundary_overlap(int *top_block, int top_stride,
942
                                 int *bottom_block, int bottom_stride,
943
                                 int *dst_block, int dst_stride, int width,
944
93.6k
                                 int height) {
945
93.6k
  if (height == 1) {
946
161k
    while (width) {
947
144k
      *dst_block = clamp((*top_block * 23 + *bottom_block * 22 + 16) >> 5,
948
144k
                         grain_min, grain_max);
949
144k
      ++top_block;
950
144k
      ++bottom_block;
951
144k
      ++dst_block;
952
144k
      --width;
953
144k
    }
954
17.2k
    return;
955
76.4k
  } else if (height == 2) {
956
1.22M
    while (width) {
957
1.14M
      dst_block[0] = clamp((27 * top_block[0] + 17 * bottom_block[0] + 16) >> 5,
958
1.14M
                           grain_min, grain_max);
959
1.14M
      dst_block[dst_stride] = clamp((17 * top_block[top_stride] +
960
1.14M
                                     27 * bottom_block[bottom_stride] + 16) >>
961
1.14M
                                        5,
962
1.14M
                                    grain_min, grain_max);
963
1.14M
      ++top_block;
964
1.14M
      ++bottom_block;
965
1.14M
      ++dst_block;
966
1.14M
      --width;
967
1.14M
    }
968
76.4k
    return;
969
76.4k
  }
970
93.6k
}
971
972
/*!\brief Add film grain
973
 *
974
 * Add film grain to an image
975
 *
976
 * Returns 0 for success, -1 for failure
977
 *
978
 * \param[in]    grain_params     Grain parameters
979
 * \param[in]    luma             luma plane
980
 * \param[in]    cb               cb plane
981
 * \param[in]    cr               cr plane
982
 * \param[in]    height           luma plane height
983
 * \param[in]    width            luma plane width
984
 * \param[in]    luma_stride      luma plane stride
985
 * \param[in]    chroma_stride    chroma plane stride
986
 */
987
static int add_film_grain_run(const aom_film_grain_t *params, uint8_t *luma,
988
                              uint8_t *cb, uint8_t *cr, int height, int width,
989
                              int luma_stride, int chroma_stride,
990
                              int use_high_bit_depth, int chroma_subsamp_y,
991
14.6k
                              int chroma_subsamp_x, int mc_identity) {
992
14.6k
  int **pred_pos_luma;
993
14.6k
  int **pred_pos_chroma;
994
14.6k
  int *luma_grain_block;
995
14.6k
  int *cb_grain_block;
996
14.6k
  int *cr_grain_block;
997
998
14.6k
  int *y_line_buf;
999
14.6k
  int *cb_line_buf;
1000
14.6k
  int *cr_line_buf;
1001
1002
14.6k
  int *y_col_buf;
1003
14.6k
  int *cb_col_buf;
1004
14.6k
  int *cr_col_buf;
1005
1006
14.6k
  random_register = params->random_seed;
1007
1008
14.6k
  int left_pad = 3;
1009
14.6k
  int right_pad = 3;  // padding to offset for AR coefficients
1010
14.6k
  int top_pad = 3;
1011
14.6k
  int bottom_pad = 0;
1012
1013
14.6k
  int ar_padding = 3;  // maximum lag used for stabilization of AR coefficients
1014
1015
14.6k
  luma_subblock_size_y = 32;
1016
14.6k
  luma_subblock_size_x = 32;
1017
1018
14.6k
  chroma_subblock_size_y = luma_subblock_size_y >> chroma_subsamp_y;
1019
14.6k
  chroma_subblock_size_x = luma_subblock_size_x >> chroma_subsamp_x;
1020
1021
  // Initial padding is only needed for generation of
1022
  // film grain templates (to stabilize the AR process)
1023
  // Only a 64x64 luma and 32x32 chroma part of a template
1024
  // is used later for adding grain, padding can be discarded
1025
1026
14.6k
  int luma_block_size_y =
1027
14.6k
      top_pad + 2 * ar_padding + luma_subblock_size_y * 2 + bottom_pad;
1028
14.6k
  int luma_block_size_x = left_pad + 2 * ar_padding + luma_subblock_size_x * 2 +
1029
14.6k
                          2 * ar_padding + right_pad;
1030
1031
14.6k
  int chroma_block_size_y = top_pad + (2 >> chroma_subsamp_y) * ar_padding +
1032
14.6k
                            chroma_subblock_size_y * 2 + bottom_pad;
1033
14.6k
  int chroma_block_size_x = left_pad + (2 >> chroma_subsamp_x) * ar_padding +
1034
14.6k
                            chroma_subblock_size_x * 2 +
1035
14.6k
                            (2 >> chroma_subsamp_x) * ar_padding + right_pad;
1036
1037
14.6k
  int luma_grain_stride = luma_block_size_x;
1038
14.6k
  int chroma_grain_stride = chroma_block_size_x;
1039
1040
14.6k
  int overlap = params->overlap_flag;
1041
14.6k
  int bit_depth = params->bit_depth;
1042
1043
14.6k
  const int grain_center = 128 << (bit_depth - 8);
1044
14.6k
  grain_min = 0 - grain_center;
1045
14.6k
  grain_max = grain_center - 1;
1046
1047
14.6k
  if (!init_arrays(params, luma_stride, chroma_stride, &pred_pos_luma,
1048
14.6k
                   &pred_pos_chroma, &luma_grain_block, &cb_grain_block,
1049
14.6k
                   &cr_grain_block, &y_line_buf, &cb_line_buf, &cr_line_buf,
1050
14.6k
                   &y_col_buf, &cb_col_buf, &cr_col_buf,
1051
14.6k
                   luma_block_size_y * luma_block_size_x,
1052
14.6k
                   chroma_block_size_y * chroma_block_size_x, chroma_subsamp_y,
1053
14.6k
                   chroma_subsamp_x))
1054
0
    return -1;
1055
1056
14.6k
  generate_luma_grain_block(params, pred_pos_luma, luma_grain_block,
1057
14.6k
                            luma_block_size_y, luma_block_size_x,
1058
14.6k
                            luma_grain_stride, left_pad, top_pad, right_pad,
1059
14.6k
                            bottom_pad);
1060
1061
14.6k
  if (!generate_chroma_grain_blocks(
1062
14.6k
          params, pred_pos_chroma, luma_grain_block, cb_grain_block,
1063
14.6k
          cr_grain_block, luma_grain_stride, chroma_block_size_y,
1064
14.6k
          chroma_block_size_x, chroma_grain_stride, left_pad, top_pad,
1065
14.6k
          right_pad, bottom_pad, chroma_subsamp_y, chroma_subsamp_x))
1066
0
    return -1;
1067
1068
14.6k
  init_scaling_function(params->scaling_points_y, params->num_y_points,
1069
14.6k
                        scaling_lut_y);
1070
1071
14.6k
  if (params->chroma_scaling_from_luma) {
1072
8.35k
    memcpy(scaling_lut_cb, scaling_lut_y, sizeof(*scaling_lut_y) * 256);
1073
8.35k
    memcpy(scaling_lut_cr, scaling_lut_y, sizeof(*scaling_lut_y) * 256);
1074
8.35k
  } else {
1075
6.28k
    init_scaling_function(params->scaling_points_cb, params->num_cb_points,
1076
6.28k
                          scaling_lut_cb);
1077
6.28k
    init_scaling_function(params->scaling_points_cr, params->num_cr_points,
1078
6.28k
                          scaling_lut_cr);
1079
6.28k
  }
1080
37.1k
  for (int y = 0; y < height / 2; y += (luma_subblock_size_y >> 1)) {
1081
22.4k
    init_random_generator(y * 2, params->random_seed);
1082
1083
75.5k
    for (int x = 0; x < width / 2; x += (luma_subblock_size_x >> 1)) {
1084
53.0k
      int offset_y = get_random_number(8);
1085
53.0k
      int offset_x = (offset_y >> 4) & 15;
1086
53.0k
      offset_y &= 15;
1087
1088
53.0k
      int luma_offset_y = left_pad + 2 * ar_padding + (offset_y << 1);
1089
53.0k
      int luma_offset_x = top_pad + 2 * ar_padding + (offset_x << 1);
1090
1091
53.0k
      int chroma_offset_y = top_pad + (2 >> chroma_subsamp_y) * ar_padding +
1092
53.0k
                            offset_y * (2 >> chroma_subsamp_y);
1093
53.0k
      int chroma_offset_x = left_pad + (2 >> chroma_subsamp_x) * ar_padding +
1094
53.0k
                            offset_x * (2 >> chroma_subsamp_x);
1095
1096
53.0k
      if (overlap && x) {
1097
20.7k
        ver_boundary_overlap(
1098
20.7k
            y_col_buf, 2,
1099
20.7k
            luma_grain_block + luma_offset_y * luma_grain_stride +
1100
20.7k
                luma_offset_x,
1101
20.7k
            luma_grain_stride, y_col_buf, 2, 2,
1102
20.7k
            AOMMIN(luma_subblock_size_y + 2, height - (y << 1)));
1103
1104
20.7k
        ver_boundary_overlap(
1105
20.7k
            cb_col_buf, 2 >> chroma_subsamp_x,
1106
20.7k
            cb_grain_block + chroma_offset_y * chroma_grain_stride +
1107
20.7k
                chroma_offset_x,
1108
20.7k
            chroma_grain_stride, cb_col_buf, 2 >> chroma_subsamp_x,
1109
20.7k
            2 >> chroma_subsamp_x,
1110
20.7k
            AOMMIN(chroma_subblock_size_y + (2 >> chroma_subsamp_y),
1111
20.7k
                   (height - (y << 1)) >> chroma_subsamp_y));
1112
1113
20.7k
        ver_boundary_overlap(
1114
20.7k
            cr_col_buf, 2 >> chroma_subsamp_x,
1115
20.7k
            cr_grain_block + chroma_offset_y * chroma_grain_stride +
1116
20.7k
                chroma_offset_x,
1117
20.7k
            chroma_grain_stride, cr_col_buf, 2 >> chroma_subsamp_x,
1118
20.7k
            2 >> chroma_subsamp_x,
1119
20.7k
            AOMMIN(chroma_subblock_size_y + (2 >> chroma_subsamp_y),
1120
20.7k
                   (height - (y << 1)) >> chroma_subsamp_y));
1121
1122
20.7k
        int i = y ? 1 : 0;
1123
1124
20.7k
        if (use_high_bit_depth) {
1125
17.2k
          add_noise_to_block_hbd(
1126
17.2k
              params,
1127
17.2k
              (uint16_t *)luma + ((y + i) << 1) * luma_stride + (x << 1),
1128
17.2k
              (uint16_t *)cb +
1129
17.2k
                  ((y + i) << (1 - chroma_subsamp_y)) * chroma_stride +
1130
17.2k
                  (x << (1 - chroma_subsamp_x)),
1131
17.2k
              (uint16_t *)cr +
1132
17.2k
                  ((y + i) << (1 - chroma_subsamp_y)) * chroma_stride +
1133
17.2k
                  (x << (1 - chroma_subsamp_x)),
1134
17.2k
              luma_stride, chroma_stride, y_col_buf + i * 4,
1135
17.2k
              cb_col_buf + i * (2 - chroma_subsamp_y) * (2 - chroma_subsamp_x),
1136
17.2k
              cr_col_buf + i * (2 - chroma_subsamp_y) * (2 - chroma_subsamp_x),
1137
17.2k
              2, (2 - chroma_subsamp_x),
1138
17.2k
              AOMMIN(luma_subblock_size_y >> 1, height / 2 - y) - i, 1,
1139
17.2k
              bit_depth, chroma_subsamp_y, chroma_subsamp_x, mc_identity);
1140
17.2k
        } else {
1141
3.48k
          add_noise_to_block(
1142
3.48k
              params, luma + ((y + i) << 1) * luma_stride + (x << 1),
1143
3.48k
              cb + ((y + i) << (1 - chroma_subsamp_y)) * chroma_stride +
1144
3.48k
                  (x << (1 - chroma_subsamp_x)),
1145
3.48k
              cr + ((y + i) << (1 - chroma_subsamp_y)) * chroma_stride +
1146
3.48k
                  (x << (1 - chroma_subsamp_x)),
1147
3.48k
              luma_stride, chroma_stride, y_col_buf + i * 4,
1148
3.48k
              cb_col_buf + i * (2 - chroma_subsamp_y) * (2 - chroma_subsamp_x),
1149
3.48k
              cr_col_buf + i * (2 - chroma_subsamp_y) * (2 - chroma_subsamp_x),
1150
3.48k
              2, (2 - chroma_subsamp_x),
1151
3.48k
              AOMMIN(luma_subblock_size_y >> 1, height / 2 - y) - i, 1,
1152
3.48k
              bit_depth, chroma_subsamp_y, chroma_subsamp_x, mc_identity);
1153
3.48k
        }
1154
20.7k
      }
1155
1156
53.0k
      if (overlap && y) {
1157
19.1k
        if (x) {
1158
12.0k
          hor_boundary_overlap(y_line_buf + (x << 1), luma_stride, y_col_buf, 2,
1159
12.0k
                               y_line_buf + (x << 1), luma_stride, 2, 2);
1160
1161
12.0k
          hor_boundary_overlap(cb_line_buf + x * (2 >> chroma_subsamp_x),
1162
12.0k
                               chroma_stride, cb_col_buf, 2 >> chroma_subsamp_x,
1163
12.0k
                               cb_line_buf + x * (2 >> chroma_subsamp_x),
1164
12.0k
                               chroma_stride, 2 >> chroma_subsamp_x,
1165
12.0k
                               2 >> chroma_subsamp_y);
1166
1167
12.0k
          hor_boundary_overlap(cr_line_buf + x * (2 >> chroma_subsamp_x),
1168
12.0k
                               chroma_stride, cr_col_buf, 2 >> chroma_subsamp_x,
1169
12.0k
                               cr_line_buf + x * (2 >> chroma_subsamp_x),
1170
12.0k
                               chroma_stride, 2 >> chroma_subsamp_x,
1171
12.0k
                               2 >> chroma_subsamp_y);
1172
12.0k
        }
1173
1174
19.1k
        hor_boundary_overlap(
1175
19.1k
            y_line_buf + ((x ? x + 1 : 0) << 1), luma_stride,
1176
19.1k
            luma_grain_block + luma_offset_y * luma_grain_stride +
1177
19.1k
                luma_offset_x + (x ? 2 : 0),
1178
19.1k
            luma_grain_stride, y_line_buf + ((x ? x + 1 : 0) << 1), luma_stride,
1179
19.1k
            AOMMIN(luma_subblock_size_x - ((x ? 1 : 0) << 1),
1180
19.1k
                   width - ((x ? x + 1 : 0) << 1)),
1181
19.1k
            2);
1182
1183
19.1k
        hor_boundary_overlap(
1184
19.1k
            cb_line_buf + ((x ? x + 1 : 0) << (1 - chroma_subsamp_x)),
1185
19.1k
            chroma_stride,
1186
19.1k
            cb_grain_block + chroma_offset_y * chroma_grain_stride +
1187
19.1k
                chroma_offset_x + ((x ? 1 : 0) << (1 - chroma_subsamp_x)),
1188
19.1k
            chroma_grain_stride,
1189
19.1k
            cb_line_buf + ((x ? x + 1 : 0) << (1 - chroma_subsamp_x)),
1190
19.1k
            chroma_stride,
1191
19.1k
            AOMMIN(chroma_subblock_size_x -
1192
19.1k
                       ((x ? 1 : 0) << (1 - chroma_subsamp_x)),
1193
19.1k
                   (width - ((x ? x + 1 : 0) << 1)) >> chroma_subsamp_x),
1194
19.1k
            2 >> chroma_subsamp_y);
1195
1196
19.1k
        hor_boundary_overlap(
1197
19.1k
            cr_line_buf + ((x ? x + 1 : 0) << (1 - chroma_subsamp_x)),
1198
19.1k
            chroma_stride,
1199
19.1k
            cr_grain_block + chroma_offset_y * chroma_grain_stride +
1200
19.1k
                chroma_offset_x + ((x ? 1 : 0) << (1 - chroma_subsamp_x)),
1201
19.1k
            chroma_grain_stride,
1202
19.1k
            cr_line_buf + ((x ? x + 1 : 0) << (1 - chroma_subsamp_x)),
1203
19.1k
            chroma_stride,
1204
19.1k
            AOMMIN(chroma_subblock_size_x -
1205
19.1k
                       ((x ? 1 : 0) << (1 - chroma_subsamp_x)),
1206
19.1k
                   (width - ((x ? x + 1 : 0) << 1)) >> chroma_subsamp_x),
1207
19.1k
            2 >> chroma_subsamp_y);
1208
1209
19.1k
        if (use_high_bit_depth) {
1210
14.7k
          add_noise_to_block_hbd(
1211
14.7k
              params, (uint16_t *)luma + (y << 1) * luma_stride + (x << 1),
1212
14.7k
              (uint16_t *)cb + (y << (1 - chroma_subsamp_y)) * chroma_stride +
1213
14.7k
                  (x << ((1 - chroma_subsamp_x))),
1214
14.7k
              (uint16_t *)cr + (y << (1 - chroma_subsamp_y)) * chroma_stride +
1215
14.7k
                  (x << ((1 - chroma_subsamp_x))),
1216
14.7k
              luma_stride, chroma_stride, y_line_buf + (x << 1),
1217
14.7k
              cb_line_buf + (x << (1 - chroma_subsamp_x)),
1218
14.7k
              cr_line_buf + (x << (1 - chroma_subsamp_x)), luma_stride,
1219
14.7k
              chroma_stride, 1,
1220
14.7k
              AOMMIN(luma_subblock_size_x >> 1, width / 2 - x), bit_depth,
1221
14.7k
              chroma_subsamp_y, chroma_subsamp_x, mc_identity);
1222
14.7k
        } else {
1223
4.45k
          add_noise_to_block(
1224
4.45k
              params, luma + (y << 1) * luma_stride + (x << 1),
1225
4.45k
              cb + (y << (1 - chroma_subsamp_y)) * chroma_stride +
1226
4.45k
                  (x << ((1 - chroma_subsamp_x))),
1227
4.45k
              cr + (y << (1 - chroma_subsamp_y)) * chroma_stride +
1228
4.45k
                  (x << ((1 - chroma_subsamp_x))),
1229
4.45k
              luma_stride, chroma_stride, y_line_buf + (x << 1),
1230
4.45k
              cb_line_buf + (x << (1 - chroma_subsamp_x)),
1231
4.45k
              cr_line_buf + (x << (1 - chroma_subsamp_x)), luma_stride,
1232
4.45k
              chroma_stride, 1,
1233
4.45k
              AOMMIN(luma_subblock_size_x >> 1, width / 2 - x), bit_depth,
1234
4.45k
              chroma_subsamp_y, chroma_subsamp_x, mc_identity);
1235
4.45k
        }
1236
19.1k
      }
1237
1238
53.0k
      int i = overlap && y ? 1 : 0;
1239
53.0k
      int j = overlap && x ? 1 : 0;
1240
1241
53.0k
      if (use_high_bit_depth) {
1242
37.2k
        add_noise_to_block_hbd(
1243
37.2k
            params,
1244
37.2k
            (uint16_t *)luma + ((y + i) << 1) * luma_stride + ((x + j) << 1),
1245
37.2k
            (uint16_t *)cb +
1246
37.2k
                ((y + i) << (1 - chroma_subsamp_y)) * chroma_stride +
1247
37.2k
                ((x + j) << (1 - chroma_subsamp_x)),
1248
37.2k
            (uint16_t *)cr +
1249
37.2k
                ((y + i) << (1 - chroma_subsamp_y)) * chroma_stride +
1250
37.2k
                ((x + j) << (1 - chroma_subsamp_x)),
1251
37.2k
            luma_stride, chroma_stride,
1252
37.2k
            luma_grain_block + (luma_offset_y + (i << 1)) * luma_grain_stride +
1253
37.2k
                luma_offset_x + (j << 1),
1254
37.2k
            cb_grain_block +
1255
37.2k
                (chroma_offset_y + (i << (1 - chroma_subsamp_y))) *
1256
37.2k
                    chroma_grain_stride +
1257
37.2k
                chroma_offset_x + (j << (1 - chroma_subsamp_x)),
1258
37.2k
            cr_grain_block +
1259
37.2k
                (chroma_offset_y + (i << (1 - chroma_subsamp_y))) *
1260
37.2k
                    chroma_grain_stride +
1261
37.2k
                chroma_offset_x + (j << (1 - chroma_subsamp_x)),
1262
37.2k
            luma_grain_stride, chroma_grain_stride,
1263
37.2k
            AOMMIN(luma_subblock_size_y >> 1, height / 2 - y) - i,
1264
37.2k
            AOMMIN(luma_subblock_size_x >> 1, width / 2 - x) - j, bit_depth,
1265
37.2k
            chroma_subsamp_y, chroma_subsamp_x, mc_identity);
1266
37.2k
      } else {
1267
15.8k
        add_noise_to_block(
1268
15.8k
            params, luma + ((y + i) << 1) * luma_stride + ((x + j) << 1),
1269
15.8k
            cb + ((y + i) << (1 - chroma_subsamp_y)) * chroma_stride +
1270
15.8k
                ((x + j) << (1 - chroma_subsamp_x)),
1271
15.8k
            cr + ((y + i) << (1 - chroma_subsamp_y)) * chroma_stride +
1272
15.8k
                ((x + j) << (1 - chroma_subsamp_x)),
1273
15.8k
            luma_stride, chroma_stride,
1274
15.8k
            luma_grain_block + (luma_offset_y + (i << 1)) * luma_grain_stride +
1275
15.8k
                luma_offset_x + (j << 1),
1276
15.8k
            cb_grain_block +
1277
15.8k
                (chroma_offset_y + (i << (1 - chroma_subsamp_y))) *
1278
15.8k
                    chroma_grain_stride +
1279
15.8k
                chroma_offset_x + (j << (1 - chroma_subsamp_x)),
1280
15.8k
            cr_grain_block +
1281
15.8k
                (chroma_offset_y + (i << (1 - chroma_subsamp_y))) *
1282
15.8k
                    chroma_grain_stride +
1283
15.8k
                chroma_offset_x + (j << (1 - chroma_subsamp_x)),
1284
15.8k
            luma_grain_stride, chroma_grain_stride,
1285
15.8k
            AOMMIN(luma_subblock_size_y >> 1, height / 2 - y) - i,
1286
15.8k
            AOMMIN(luma_subblock_size_x >> 1, width / 2 - x) - j, bit_depth,
1287
15.8k
            chroma_subsamp_y, chroma_subsamp_x, mc_identity);
1288
15.8k
      }
1289
1290
53.0k
      if (overlap) {
1291
36.8k
        if (x) {
1292
          // Copy overlapped column bufer to line buffer
1293
20.7k
          copy_area(y_col_buf + (luma_subblock_size_y << 1), 2,
1294
20.7k
                    y_line_buf + (x << 1), luma_stride, 2, 2);
1295
1296
20.7k
          copy_area(
1297
20.7k
              cb_col_buf + (chroma_subblock_size_y << (1 - chroma_subsamp_x)),
1298
20.7k
              2 >> chroma_subsamp_x,
1299
20.7k
              cb_line_buf + (x << (1 - chroma_subsamp_x)), chroma_stride,
1300
20.7k
              2 >> chroma_subsamp_x, 2 >> chroma_subsamp_y);
1301
1302
20.7k
          copy_area(
1303
20.7k
              cr_col_buf + (chroma_subblock_size_y << (1 - chroma_subsamp_x)),
1304
20.7k
              2 >> chroma_subsamp_x,
1305
20.7k
              cr_line_buf + (x << (1 - chroma_subsamp_x)), chroma_stride,
1306
20.7k
              2 >> chroma_subsamp_x, 2 >> chroma_subsamp_y);
1307
20.7k
        }
1308
1309
        // Copy grain to the line buffer for overlap with a bottom block
1310
36.8k
        copy_area(
1311
36.8k
            luma_grain_block +
1312
36.8k
                (luma_offset_y + luma_subblock_size_y) * luma_grain_stride +
1313
36.8k
                luma_offset_x + ((x ? 2 : 0)),
1314
36.8k
            luma_grain_stride, y_line_buf + ((x ? x + 1 : 0) << 1), luma_stride,
1315
36.8k
            AOMMIN(luma_subblock_size_x, width - (x << 1)) - (x ? 2 : 0), 2);
1316
1317
36.8k
        copy_area(cb_grain_block +
1318
36.8k
                      (chroma_offset_y + chroma_subblock_size_y) *
1319
36.8k
                          chroma_grain_stride +
1320
36.8k
                      chroma_offset_x + (x ? 2 >> chroma_subsamp_x : 0),
1321
36.8k
                  chroma_grain_stride,
1322
36.8k
                  cb_line_buf + ((x ? x + 1 : 0) << (1 - chroma_subsamp_x)),
1323
36.8k
                  chroma_stride,
1324
36.8k
                  AOMMIN(chroma_subblock_size_x,
1325
36.8k
                         ((width - (x << 1)) >> chroma_subsamp_x)) -
1326
36.8k
                      (x ? 2 >> chroma_subsamp_x : 0),
1327
36.8k
                  2 >> chroma_subsamp_y);
1328
1329
36.8k
        copy_area(cr_grain_block +
1330
36.8k
                      (chroma_offset_y + chroma_subblock_size_y) *
1331
36.8k
                          chroma_grain_stride +
1332
36.8k
                      chroma_offset_x + (x ? 2 >> chroma_subsamp_x : 0),
1333
36.8k
                  chroma_grain_stride,
1334
36.8k
                  cr_line_buf + ((x ? x + 1 : 0) << (1 - chroma_subsamp_x)),
1335
36.8k
                  chroma_stride,
1336
36.8k
                  AOMMIN(chroma_subblock_size_x,
1337
36.8k
                         ((width - (x << 1)) >> chroma_subsamp_x)) -
1338
36.8k
                      (x ? 2 >> chroma_subsamp_x : 0),
1339
36.8k
                  2 >> chroma_subsamp_y);
1340
1341
        // Copy grain to the column buffer for overlap with the next block to
1342
        // the right
1343
1344
36.8k
        copy_area(luma_grain_block + luma_offset_y * luma_grain_stride +
1345
36.8k
                      luma_offset_x + luma_subblock_size_x,
1346
36.8k
                  luma_grain_stride, y_col_buf, 2, 2,
1347
36.8k
                  AOMMIN(luma_subblock_size_y + 2, height - (y << 1)));
1348
1349
36.8k
        copy_area(cb_grain_block + chroma_offset_y * chroma_grain_stride +
1350
36.8k
                      chroma_offset_x + chroma_subblock_size_x,
1351
36.8k
                  chroma_grain_stride, cb_col_buf, 2 >> chroma_subsamp_x,
1352
36.8k
                  2 >> chroma_subsamp_x,
1353
36.8k
                  AOMMIN(chroma_subblock_size_y + (2 >> chroma_subsamp_y),
1354
36.8k
                         (height - (y << 1)) >> chroma_subsamp_y));
1355
1356
36.8k
        copy_area(cr_grain_block + chroma_offset_y * chroma_grain_stride +
1357
36.8k
                      chroma_offset_x + chroma_subblock_size_x,
1358
36.8k
                  chroma_grain_stride, cr_col_buf, 2 >> chroma_subsamp_x,
1359
36.8k
                  2 >> chroma_subsamp_x,
1360
36.8k
                  AOMMIN(chroma_subblock_size_y + (2 >> chroma_subsamp_y),
1361
36.8k
                         (height - (y << 1)) >> chroma_subsamp_y));
1362
36.8k
      }
1363
53.0k
    }
1364
22.4k
  }
1365
1366
14.6k
  dealloc_arrays(params, &pred_pos_luma, &pred_pos_chroma, &luma_grain_block,
1367
14.6k
                 &cb_grain_block, &cr_grain_block, &y_line_buf, &cb_line_buf,
1368
14.6k
                 &cr_line_buf, &y_col_buf, &cb_col_buf, &cr_col_buf);
1369
14.6k
  return 0;
1370
14.6k
}
1371
1372
int av1_add_film_grain(const aom_film_grain_t *params, const aom_image_t *src,
1373
14.6k
                       aom_image_t *dst) {
1374
14.6k
  uint8_t *luma, *cb, *cr;
1375
14.6k
  int height, width, luma_stride, chroma_stride;
1376
14.6k
  int use_high_bit_depth = 0;
1377
14.6k
  int chroma_subsamp_x = 0;
1378
14.6k
  int chroma_subsamp_y = 0;
1379
14.6k
  int mc_identity = src->mc == AOM_CICP_MC_IDENTITY ? 1 : 0;
1380
1381
14.6k
  switch (src->fmt) {
1382
0
    case AOM_IMG_FMT_AOMI420:
1383
1.71k
    case AOM_IMG_FMT_I420:
1384
1.71k
      use_high_bit_depth = 0;
1385
1.71k
      chroma_subsamp_x = 1;
1386
1.71k
      chroma_subsamp_y = 1;
1387
1.71k
      break;
1388
5.41k
    case AOM_IMG_FMT_I42016:
1389
5.41k
      use_high_bit_depth = 1;
1390
5.41k
      chroma_subsamp_x = 1;
1391
5.41k
      chroma_subsamp_y = 1;
1392
5.41k
      break;
1393
      //    case AOM_IMG_FMT_444A:
1394
1.04k
    case AOM_IMG_FMT_I444:
1395
1.04k
      use_high_bit_depth = 0;
1396
1.04k
      chroma_subsamp_x = 0;
1397
1.04k
      chroma_subsamp_y = 0;
1398
1.04k
      break;
1399
4.12k
    case AOM_IMG_FMT_I44416:
1400
4.12k
      use_high_bit_depth = 1;
1401
4.12k
      chroma_subsamp_x = 0;
1402
4.12k
      chroma_subsamp_y = 0;
1403
4.12k
      break;
1404
2.18k
    case AOM_IMG_FMT_I422:
1405
2.18k
      use_high_bit_depth = 0;
1406
2.18k
      chroma_subsamp_x = 1;
1407
2.18k
      chroma_subsamp_y = 0;
1408
2.18k
      break;
1409
140
    case AOM_IMG_FMT_I42216:
1410
140
      use_high_bit_depth = 1;
1411
140
      chroma_subsamp_x = 1;
1412
140
      chroma_subsamp_y = 0;
1413
140
      break;
1414
0
    default:  // unknown input format
1415
0
      fprintf(stderr, "Film grain error: input format is not supported!");
1416
0
      return -1;
1417
14.6k
  }
1418
1419
14.6k
  assert(params->bit_depth == src->bit_depth);
1420
1421
14.6k
  dst->fmt = src->fmt;
1422
14.6k
  dst->bit_depth = src->bit_depth;
1423
1424
14.6k
  dst->r_w = src->r_w;
1425
14.6k
  dst->r_h = src->r_h;
1426
14.6k
  dst->d_w = src->d_w;
1427
14.6k
  dst->d_h = src->d_h;
1428
1429
14.6k
  dst->cp = src->cp;
1430
14.6k
  dst->tc = src->tc;
1431
14.6k
  dst->mc = src->mc;
1432
1433
14.6k
  dst->monochrome = src->monochrome;
1434
14.6k
  dst->csp = src->csp;
1435
14.6k
  dst->range = src->range;
1436
1437
14.6k
  dst->x_chroma_shift = src->x_chroma_shift;
1438
14.6k
  dst->y_chroma_shift = src->y_chroma_shift;
1439
1440
14.6k
  dst->temporal_id = src->temporal_id;
1441
14.6k
  dst->spatial_id = src->spatial_id;
1442
1443
14.6k
  width = src->d_w % 2 ? src->d_w + 1 : src->d_w;
1444
14.6k
  height = src->d_h % 2 ? src->d_h + 1 : src->d_h;
1445
1446
14.6k
  copy_rect(src->planes[AOM_PLANE_Y], src->stride[AOM_PLANE_Y],
1447
14.6k
            dst->planes[AOM_PLANE_Y], dst->stride[AOM_PLANE_Y], src->d_w,
1448
14.6k
            src->d_h, use_high_bit_depth);
1449
  // Note that dst is already assumed to be aligned to even.
1450
14.6k
  extend_even(dst->planes[AOM_PLANE_Y], dst->stride[AOM_PLANE_Y], src->d_w,
1451
14.6k
              src->d_h, use_high_bit_depth);
1452
1453
14.6k
  if (!src->monochrome) {
1454
14.5k
    copy_rect(src->planes[AOM_PLANE_U], src->stride[AOM_PLANE_U],
1455
14.5k
              dst->planes[AOM_PLANE_U], dst->stride[AOM_PLANE_U],
1456
14.5k
              width >> chroma_subsamp_x, height >> chroma_subsamp_y,
1457
14.5k
              use_high_bit_depth);
1458
1459
14.5k
    copy_rect(src->planes[AOM_PLANE_V], src->stride[AOM_PLANE_V],
1460
14.5k
              dst->planes[AOM_PLANE_V], dst->stride[AOM_PLANE_V],
1461
14.5k
              width >> chroma_subsamp_x, height >> chroma_subsamp_y,
1462
14.5k
              use_high_bit_depth);
1463
14.5k
  }
1464
1465
14.6k
  luma = dst->planes[AOM_PLANE_Y];
1466
14.6k
  cb = dst->planes[AOM_PLANE_U];
1467
14.6k
  cr = dst->planes[AOM_PLANE_V];
1468
1469
  // luma and chroma strides in samples
1470
14.6k
  luma_stride = dst->stride[AOM_PLANE_Y] >> use_high_bit_depth;
1471
14.6k
  chroma_stride = dst->stride[AOM_PLANE_U] >> use_high_bit_depth;
1472
1473
14.6k
  return add_film_grain_run(params, luma, cb, cr, height, width, luma_stride,
1474
14.6k
                            chroma_stride, use_high_bit_depth, chroma_subsamp_y,
1475
14.6k
                            chroma_subsamp_x, mc_identity);
1476
14.6k
}