ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia), 2021

Learning to Reconstruct Botanical Trees
from Single Images

Bosheng Li1       Jacek Kałużny2       Jonathan Klein3       Dominik L. Michels4      
Wojciech Pałubicki2       Bedrich Benes1       Sören Pirk5

1Purdue University
2Adam Mickiewicz University
3University of Bonn
5Google Research


We introduce a novel method for reconstructing the 3D geometry of botanical trees from single photographs. Faithfully reconstructing a tree from single-view sensor data is a challenging and open problem because many possible 3D trees exist that fit the tree's shape observed from a single view. We address this challenge by defining a reconstruction pipeline based on three neural networks. The networks simultaneously mask out trees in input photographs, identify a tree's species, and obtain its 3D radial bounding volume -- our novel 3D representation for botanical trees. Radial bounding volumes (RBV) are used to orchestrate a procedural model primed on learned parameters to grow a tree that matches the main branching structure and the overall shape of the captured tree. While the RBV allows us to faithfully reconstruct the main branching structure, we use the procedural model's morphological constraints to generate realistic branching for the tree crown. This constraints the number of solutions of tree models for a given photograph of a tree. We show that our method reconstructs various tree species even when the trees are captured in front of complex backgrounds. Moreover, although our neural networks have been trained on synthetic data with data augmentation, we show that our pipeline performs well for real tree photographs. We evaluate the reconstructed geometries with several metrics, including leaf area index and maximum radial tree distances.





  author    = {Bosheng Li and Jacek Ka{\l}u{\.z}ny and Jonathan Klein and Dominik L.~Michels 
               and Wojtek Pa{\l}ubicki and Bedrich Benes and S\"oren Pirk},
  title     = {Learning to Reconstruct Botanical Trees from Single Images},
  journal   = {ACM Transaction on Graphics},
  year      = {2021},
  month     = {12},
  volume    = {40},
  number    = {6},
  articleno = {231},
  doi       = {},
  publisher = {ACM},
  address   = {New York, NY, USA}