Affiliation:
1. College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China
2. Simon Fraser University, Vancouver, Canada
3. Tel Aviv University, Tel Aviv, Israel
Abstract
We introduce a novel method for acquiring boundary representations (B-Reps) of 3D CAD models which involves a two-step process: it first applies a
spatial partitioning
, referred to as the "split", followed by a "fit" operation to derive a single primitive within each partition. Specifically, our partitioning aims to produce the classical
Voronoi diagram
of the set of ground-truth (GT) B-Rep primitives. In contrast to prior B-Rep constructions which were bottom-up, either via direct primitive fitting or point clustering, our Split-and-Fit approach is
top-down
and
structure-aware
, since a Voronoi partition explicitly reveals both the number of and the connections between the primitives. We design a neural network to predict the Voronoi diagram from an input point cloud or distance field via a binary classification. We show that our network, coined NVD-Net for neural Voronoi diagrams, can effectively learn Voronoi partitions for CAD models from training data and exhibits superior generalization capabilities. Extensive experiments and evaluation demonstrate that the resulting B-Reps, consisting of parametric surfaces, curves, and vertices, are more plausible than those obtained by existing alternatives, with significant improvements in reconstruction quality. Code will be released on https://github.com/yilinliu77/NVDNet.
Funder
NSFC
Guangdong Basic and Applied Basic Research Foundation
DEGP Innovation Team
Shenzhen Science and Technology Program
Publisher
Association for Computing Machinery (ACM)
Reference48 articles.
1. Pierre Alliez, David Cohen-Steiner, Yiying Tong, and Mathieu Desbrun. 2007. Voronoi-based variational reconstruction of unoriented point sets. In Proc. Eurographics Symp. on Geometry Processing, Vol. 257. 39--48.
2. Hierarchical Structure Recovery of Point-Sampled Surfaces
3. Kinetic Shape Reconstruction
4. On Visual Similarity Based 3D Model Retrieval
5. Neural dual contouring