We introduce an inverse procedural modeling approach that learns L-system representations of pixel images with branching structures. Our fully automatic model generates a compact set of textual rewriting rules that describe the input. We use deep learning to discover atomic structures such as line segments or branchings. Orientation and scaling of these structures are determined and the detected structures are combined into a tree. The initial representation is analyzed, and repeating parts are encoded into a small grammar by using greedy optimization while the user can control the size of the detected rules. The output is an L-system that represents the input image as a simple text and a set of terminal symbols. We apply our approach to a variety of examples, demonstrate its robustness against noise and blur, and we show that it can detect user sketches and complex input structures.
@article{Guo2020InverseProceduralModeling, author = {J. Guo, H. Jiang, B. Benes, O. Deussen, X. Zhang, D. Lischinski, H. Huang}, doi = {10.1145/3394105}, journal = {ACM Transactions on Graphics}, month = {sep}, number = {5}, pages = {1--13}, publisher = {Association for Computing Machinery}, title = {Inverse Procedural Modeling of Branching Structures by Inferring L-Systems}, url = {http://graphics.uni-konstanz.de/publikationen/Guo2020InverseProceduralModeling}, volume = {39}, year = {2020} }