HiFi-BRep：用於穩健B-Rep生成的高保真潛在表示

摘要

邊界表示（B-Rep）生成是計算機輔助設計中的一項基本任務，然而直接合成高保真度且結構有效的B-Rep仍然是一項重大挑戰。現有的深度生成方法存在兩種脆弱性：表示脆弱性，源於潛在空間中的填充噪聲與特徵污染；以及生成脆弱性，源於序列誤差傳播以及因不可微分的有效性約束而導致的訓練-推理不匹配。我們提出HiFi-BRep，一種新穎框架，通過兩項協同貢獻解決上述局限。首先，拓撲感知編碼器通過可學習查詢消除填充，並利用拓撲引導的注意力機制防止特徵污染，從而構建高保真度的潛在表示。其次，單階段解碼器同時並行預測幾何與拓撲，並將核心流形約束嵌入為可微分的學習目標。該設計確保幾何與拓撲之間的相互引導，同時避免級聯誤差。大量實驗表明，HiFi-BRep在結構有效性和幾何保真度方面均顯著優於最先進的方法，為高質量的B-Rep合成提供了穩健的解決方案。程式碼與模型公開於 https://github.com/1nnoh/HiFi-BRep。

English

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.