HiFi-BRep：面向鲁棒 B-Rep 生成的高保真潜变量表示
HiFi-BRep: High-Fidelity Latent Representation for Robust B-Rep Generation
把 B-Rep 生成重构为「高保真潜变量 + 单阶段并行几何/拓扑解码」的范式，其用可学习查询消除 padding 噪声、用拓扑引导注意力防止特征污染的做法，可迁移到点云/网格等结构化 3D 表示的生成式建模中。
原文依据 a topology-aware encoder constructs a high-fidelity latent representation by eliminating padding via learnable queries
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论边界表示（B-Rep）生成是计算机辅助设计中的一项基础任务，然而直接合成高保真且结构有效的 B-Rep 仍是一项重大挑战。现有的深度生成方法存在两类脆弱性：一是表示脆弱性，由潜变量空间中的填充噪声与特征污染引起；二是生成脆弱性，源于序列化的误差传播以及由不可微的有效性约束所导致的训练-推理失配。我们提出 HiFi-BRep，一个通过两项协同贡献来克服上述局限的新框架。首先，拓扑感知编码器通过可学习查询消除填充，并借助拓扑引导注意力防止特征污染，从而构建高保真潜变量表示。其次，单阶段解码器并行地联合预测几何与拓扑，将核心流形约束作为可微的学习目标嵌入其中。该设计保证了几何与拓扑之间的相互引导，同时避免了级联误差。大量实验表明，HiFi-BRep 在结构有效性与几何保真度两方面均显著优于最优方法，为高质量 B-Rep 合成提供了鲁棒的解决方案。代码与模型已公开于 https://github.com/1nnoh/HiFi-BRep。
英文原文摘要 1358 字符
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.