HiFi-BRep: High-Fidelity Latent Representation for Robust B-Rep Generation

2026-08-17

AI Summary

This study addresses the challenge of achieving high-fidelity structural validity in B-Rep generation caused by fragile representations and generation processes. We propose a topology-aware encoder that constructs a robust latent space to eliminate noise, alongside a single-stage parallel decoder embedding differentiable manifold constraints for joint geometric and topological prediction, thereby avoiding cascading errors. By leveraging topology-guided attention and learnable query mechanisms, this approach significantly enhances synthesis quality. Experimental results demonstrate that our model substantially outperforms state-of-the-art methods in both structural validity and geometric fidelity, establishing a new paradigm for high-fidelity 3D CAD generation.

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.

Problem

• B-Rep generation
• representation brittleness
• generation brittleness
• structural validity
• geometric fidelity

Innovation

• Topology-aware Encoder
• Single-stage Decoder
• Differentiable Manifold Constraints
• High-Fidelity Latent Representation
• Parallel Geometry-Topology Prediction