Qualitative Results
Our method generates B-rep models with enhanced structural validity and geometric fidelity, as demonstrated by the generated examples.
Boundary representation (B-rep) of geometric models is a fundamental format in Computer-Aided Design (CAD). However, automatically generating valid and high-quality B-rep models remains challenging due to the complex interdependence between the topology and geometry of the models. Existing methods tend to prioritize geometric representation while giving insufficient attention to topological constraints, making it difficult to maintain structural validity and geometric accuracy.
In this paper, we propose DTGBrepGen, a novel topology-geometry decoupled framework for B-rep generation that explicitly addresses both aspects. Our approach first generates valid topological structures through a two-stage process that independently models edge-face and edge-vertex adjacency relationships. Subsequently, we employ Transformer-based diffusion models for sequential geometry generation, progressively generating vertex coordinates, followed by edge geometries and face geometries which are represented as B-splines.
Extensive experiments on diverse CAD datasets show that DTGBrepGen significantly outperforms existing methods in both topological validity and geometric accuracy, achieving higher validity rates and producing more diverse and realistic B-reps.
Our method generates B-rep models with enhanced structural validity and geometric fidelity, as demonstrated by the generated examples.
Our method generates more realistic and geometrically precise B-rep models than baseline approaches (DeepCAD and BrepGen) on the DeepCAD dataset.
Examples of class-conditioned generation on the Furniture dataset, with distinct colors representing different categories.
B-rep models generated based on input point clouds. Each example consists of a point cloud alongside three corresponding generated B-reps
