UV-Net: Learning from Boundary Representations

TL;DR

UV-Net is a new neural network architecture that directly processes boundary representation data from 3D CAD models, effectively capturing geometric and topological information for shape analysis.

Contribution

The paper introduces UV-Net, a novel architecture combining image and graph convolutions to operate on B-rep data, along with a synthetic dataset for training and evaluation.

Findings

UV-Net outperforms point cloud, voxel, and mesh-based methods.

It generalizes well across multiple datasets.

The approach efficiently models both geometry and topology.

Abstract

We introduce UV-Net, a novel neural network architecture and representation designed to operate directly on Boundary representation (B-rep) data from 3D CAD models. The B-rep format is widely used in the design, simulation and manufacturing industries to enable sophisticated and precise CAD modeling operations. However, B-rep data presents some unique challenges when used with modern machine learning due to the complexity of the data structure and its support for both continuous non-Euclidean geometric entities and discrete topological entities. In this paper, we propose a unified representation for B-rep data that exploits the U and V parameter domain of curves and surfaces to model geometry, and an adjacency graph to explicitly model topology. This leads to a unique and efficient network architecture, UV-Net, that couples image and graph convolutional neural networks in a compute and memory-efficient manner. To aid in future research we present a synthetic labelled B-rep dataset, SolidLetters, derived from human designed fonts with variations in both geometry and topology. Finally we demonstrate that UV-Net can generalize to supervised and unsupervised tasks on five datasets, while outperforming alternate 3D shape representations such as point clouds, voxels, and meshes.