| ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generation |
| Haoxiang Guo1,3, Shilin Liu2,3, Hao Pan3, Yang Liu3, Xin Tong3, Baining Guo3 |
| 1Tsinghua University, 2University of Science and Technology of China, 3Microsoft Research Asia |
| ACM Transactions on Graphics (SIGGRAPH 2022) |
| |
 |
|
ComplexGen for CAD reconstruction from point clouds. Given an input point cloud, ComplexGen recovers corners, curves and patches simultaneously along with their mutual topology constraints, which enables more complete, regularized and structured CAD reconstruction in the boundary representation (B-Rep). For each example, the input points, the reconstructed corners (yellow) and curves (blue) and the full B-Rep models (surface patched randomly colored) are shown. The input points for (c) are corrupted by noise and those for (d) are only partial.
|
| Abstract |
|
We view the reconstruction of CAD models in the boundary representation (B-Rep) as the detection of geometric primitives of different orders, i.e. , vertices, edges and surface patches, and the correspondence of primitives, which are holistically modeled as a chain complex, and show that by modeling such comprehensive structures more complete and regularized reconstructions can be achieved. We solve the complex generation problem in two steps. First, we propose a novel neural framework that consists of a sparse CNN encoder for input point cloud processing and a tri-path transformer decoder for generating geometric primitives and their mutual relationships with estimated probabilities. Second, given the probabilistic structure predicted by the neural network, we recover a definite B-Rep chain complex by solving a global optimization maximizing the likelihood under structural validness constraints and applying geometric refinements. Extensive tests on large scale CAD datasets demonstrate that the modeling of B-Rep chain complex structure enables more accurate detection for learning and more constrained reconstruction for optimization, leading to structurally more faithful and complete CAD B-Rep models than previous results.
|
 |
|
Paper [PDF] [Arxiv]
Code and data [Link]
Supplemental doc [ZIP]
Citation
Haoxiang Guo, Shilin Liu, Hao Pan, Yang Liu, Xin Tong, and Baining Guo. 2022. ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generation. ACM
Trans. Graph. 41, 4, Article 129 (July 2022), 18 pages. https://doi.org/10.1145/3528223.3530078
(bibtex)
|
|
| |
| |
| |
| |
| ©Hao Pan. Last update: May 13, 2022. |