CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing

Daxuan Ren, Jianmin Zheng, Jianfei Cai, Jiatong Li, Haiyong Jiang, Zhongang Cai, Junzhe Zhang, Liang Pan, Mingyuan Zhang, Haiyu Zhao, Shuai Yi; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 12478-12487

Abstract


Generating an interpretable and compact representation of 3D shapes from point clouds is an important and challenging problem. This paper presents CSG-Stump Net, an unsupervised end-to-end network for learning shapes from point clouds and discovering the underlying constituent modeling primitives and operations as well. At the core is a three-level structure called CSG-Stump , consisting of a complement layer at the bottom, an intersection layer in the middle, and a union layer at the top. CSG-Stump is proven to be equivalent to CSG in terms of representation, therefore inheriting the interpretable, compact and editable nature of CSG while freeing from CSG's complex tree structures. Particularly, the CSG-Stump has a simple and regular structure, allowing neural networks to give outputs of a constant dimensionality, which makes itself deep-learning friendly. Due to these characteristics of CSG-Stump, CSG-Stump Net achieves superior results compared to previous CSG-based methods and generates much more appealing shapes, as confirmed by extensive experiment

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Ren_2021_ICCV, author = {Ren, Daxuan and Zheng, Jianmin and Cai, Jianfei and Li, Jiatong and Jiang, Haiyong and Cai, Zhongang and Zhang, Junzhe and Pan, Liang and Zhang, Mingyuan and Zhao, Haiyu and Yi, Shuai}, title = {CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {12478-12487} }