HiFi-BRep: High-Fidelity Latent Representation for Robust B-Rep Generation
2026-08-17 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address challenges in creating accurate and reliable 3D shape models used in design software. They identify two main problems in existing AI methods: noise in the data representation and errors during step-by-step shape generation. To fix this, they developed HiFi-BRep, which uses a smarter encoder that understands shape structure and a decoder that predicts shape features all at once, ensuring better quality and fewer mistakes. Their experiments show it works better than previous methods in making structurally correct and detailed 3D models.
Boundary RepresentationB-RepComputer-Aided DesignDeep Generative ModelsLatent SpaceTopology-Aware EncoderGeometry-Topology IntegrationManifold ConstraintsDecoderStructural Validity
Authors
Junhao Hou, Chenqi Luo, Pufan Wang, Jiaying Lu, Yusheng Liu, Feiwei Qin, Meie Fang, Kun Zhou
Abstract
Boundary representation (B-Rep) generation is a fundamental task in computer-aided design, yet the direct synthesis of high-fidelity and structurally valid B-Reps remains a major challenge. Existing deep generative methods suffer from two forms of brittleness: representation brittleness, caused by padding noise and feature contamination in the latent space, and generation brittleness, stemming from sequential error propagation and a train-inference mismatch due to non-differentiable validity enforcement. We propose HiFi-BRep, a novel framework that addresses these limitations through two synergistic contributions. First, a topology-aware encoder constructs a high-fidelity latent representation by eliminating padding via learnable queries and preventing feature contamination with topology-guided attention. Second, a single-stage decoder jointly predicts geometry and topology in parallel, embedding core manifold constraints as a differentiable learning objective. This design ensures mutual guidance between geometry and topology while avoiding cascaded errors. Extensive experiments show that HiFi-BRep significantly outperforms state-of-the-art methods in both structural validity and geometric fidelity, providing a robust solution for high-quality B-Rep synthesis. Code and models are publicly available at https://github.com/1nnoh/HiFi-BRep.