AutoBrep: Autoregressive B-Rep Generation with Unified Topology and Geometry

2025-12-02

AI Summary

Generating boundary-representation (B-Rep) CAD models with both precise geometry and watertight topology remains challenging. This paper proposes an end-to-end autoregressive framework: we design a unified discrete tokenization scheme that jointly encodes geometric primitives (e.g., planes, cylinders) and topological relationships (e.g., face adjacency, loop membership) into a sequence, ordered via breadth-first traversal to ensure structural consistency; we further introduce implicit geometric tokens and topological reference tokens to enable geometry–topology co-modeling within a Transformer architecture. The method natively supports B-Rep auto-completion and interactive user editing. Experiments demonstrate that our approach achieves significantly higher generation fidelity on complex solid models compared to existing baselines, exhibiting strong scalability, high geometric accuracy, and efficient inference.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Diffusion Models for Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The boundary representation (B-Rep) is the standard data structure used in Computer-Aided Design (CAD) for defining solid models. Despite recent progress, directly generating B-Reps end-to-end with precise geometry and watertight topology remains a challenge. This paper presents AutoBrep, a novel Transformer model that autoregressively generates B-Reps with high quality and validity. AutoBrep employs a unified tokenization scheme that encodes both geometric and topological characteristics of a B-Rep model as a sequence of discrete tokens. Geometric primitives (i.e., surfaces and curves) are encoded as latent geometry tokens, and their structural relationships are defined as special topological reference tokens. Sequence order in AutoBrep naturally follows a breadth first traversal of the B-Rep face adjacency graph. At inference time, neighboring faces and edges along with their topological structure are progressively generated. Extensive experiments demonstrate the advantages of our unified representation when coupled with next-token prediction for B-Rep generation. AutoBrep outperforms baselines with better quality and watertightness. It is also highly scalable to complex solids with good fidelity and inference speed. We further show that autocompleting B-Reps is natively supported through our unified tokenization, enabling user-controllable CAD generation with minimal changes. Code is available at https://github.com/AutodeskAILab/AutoBrep.

Problem

• Generating watertight B-Rep CAD models with precise geometry and topology
• Creating unified representation encoding both geometric primitives and topological relationships
• Autoregressively producing valid B-Reps that scale to complex solid models

Innovation

• Transformer autoregressively generates B-Rep sequences
• Unified tokenization encodes geometry and topology as tokens
• Breadth-first traversal order enables progressive face generation