提出新型拓扑保持网格生成方法，提升复杂网格生成质量与压缩效率。
Topology-Preserved Auto-regressive Mesh Generation in the Manner of Weaving Silk
- 通过顶点分层排序构建拓扑框架，生成时保持网格连通性与结构一致性。
- 在压缩率和每面比特数上达到当前最优，且生成网格具高几何完整性。
- 支持非流形数据在线处理，减少人工标注成本，适合大规模网格建模应用。
现有自回归网格生成方法在拓扑保持方面表现不佳，根源在于传统网格标记化将网格视为等价三角形的简单集合，生成过程中缺乏对整体拓扑结构的感知。为此，本文提出一种新型网格标记化算法，通过顶点分层与排序建立规范拓扑框架，确保生成网格具备流形性、封闭性、面法向一致性及部件感知等关键几何特性。在压缩比（Compression Ratio）和每面比特数（Bits-per-face）指标上，达到当前最优性能。此外，引入在线非流形数据处理算法与训练重采样策略，扩大可训练数据集规模，避免高昂的人工数据清洗成本。实验表明，该方法不仅能生成复杂网格，还显著提升几何完整性。
原文摘要 · Abstract (English)
Existing auto-regressive mesh generation approaches suffer from ineffective topology preservation, which is crucial for practical applications. This limitation stems from previous mesh tokenization methods treating meshes as simple collections of equivalent triangles, lacking awareness of the overall topological structure during generation. To address this issue, we propose a novel mesh tokenization algorithm that provides a canonical topological framework through vertex layering and ordering, ensuring critical geometric properties including manifoldness, watertightness, face normal consistency, and part awareness in the generated meshes. Measured by Compression Ratio and Bits-per-face, we also achieved state-of-the-art compression efficiency. Furthermore, we introduce an online non-manifold data processing algorithm and a training resampling strategy to expand the scale of trainable dataset and avoid costly manual data curation. Experimental results demonstrate the effectiveness of our approach, showcasing not only intricate mesh generation but also significantly improved geometric integrity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。