提出无等值面的高保真3D体素表示，支持任意网格且精度达10^{-5}级
Faithful Contouring: Near-Lossless 3D Voxel Representation Free from Iso-surface
- 不依赖等值面提取，直接构建稀疏体素表示
- 距离误差低至10^{-5}，重建时切比雪夫距离降低93%
- 适合需要高精度几何保持的3D生成与重建任务
准确高效的3D网格体素化表示是3D重建与生成的基础。然而，现有基于等值面的方法严重依赖封闭化或渲染优化，不可避免地损害几何保真度。本文提出Faithful Contouring，一种无需将网格转为场函数或在重采样中提取等值面的稀疏体素表示，可支持2048+分辨率，适用于任意网格。该方法通过保留锐边和内部结构实现近无损保真，即使在复杂几何与拓扑下依然有效。此外，该表示支持贴图、操作与编辑。我们还设计了一种双模式自编码器，实现可扩展且细节保留的形状重建。大量实验表明，无论是直接表示还是重建任务，Faithful Contouring均优于现有方法：直接表示的距离误差达到10^{-5}量级；在网格重建中，切比雪夫距离降低93%，F-score提升35%，证实其在3D学习任务中具有优越保真性。
原文摘要 · Abstract (English)
Accurate and efficient voxelized representations of 3D meshes are the foundation of 3D reconstruction and generation. However, existing representations based on iso-surface heavily rely on water-tightening or rendering optimization, which inevitably compromise geometric fidelity. We propose Faithful Contouring, a sparse voxelized representation that supports 2048+ resolutions for arbitrary meshes, requiring neither converting meshes to field functions nor extracting the isosurface during remeshing. It achieves near-lossless fidelity by preserving sharpness and internal structures, even for challenging cases with complex geometry and topology. The proposed method also shows flexibility for texturing, manipulation, and editing. Beyond representation, we design a dual-mode autoencoder for Faithful Contouring, enabling scalable and detail-preserving shape reconstruction. Extensive experiments show that Faithful Contouring surpasses existing methods in accuracy and efficiency for both representation and reconstruction. For direct representation, it achieves distance errors at the $10^{-5}$ level; for mesh reconstruction, it yields a 93\% reduction in Chamfer Distance and a 35\% improvement in F-score over strong baselines, confirming superior fidelity as a representation for 3D learning tasks.
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。