HiDiGen: Hierarchical Diffusion for B-Rep Generation with Explicit Topological Constraints

TL;DR

HiDiGen introduces a hierarchical diffusion framework for B-rep generation that explicitly models topological constraints, enabling the creation of valid, diverse, and complex CAD models.

Contribution

The paper presents a novel hierarchical diffusion approach that decouples geometry and topology, improving validity and diversity in B-rep generation.

Findings

Achieves high validity in generated B-rep models.

Produces diverse and novel CAD shapes.

Maintains topological consistency through explicit constraints.

Abstract

Boundary representation (B-rep) is the standard 3D modeling format in CAD systems, encoding both geometric primitives and topological connectivity. Despite its prevalence, deep generative modeling of valid B-rep structures remains challenging due to the intricate interplay between discrete topology and continuous geometry. In this paper, we propose HiDiGen, a hierarchical generation framework that decouples geometry modeling into two stages, each guided by explicitly modeled topological constraints. Specifically, our approach first establishes face-edge incidence relations to define a coherent topological scaffold, upon which face proxies and initial edge curves are generated. Subsequently, multiple Transformer-based diffusion modules are employed to refine the geometry by generating precise face surfaces and vertex positions, with edge-vertex adjacencies dynamically established and enforced to preserve structural consistency. This progressive geometry hierarchy enables the generation of more novel and diverse shapes, while two-stage topological modeling ensures high validity. Experimental results show that HiDiGen achieves strong performance, generating novel, diverse, and topologically sound CAD models.