超越UV映射：通过表面对齐纹理场实现网格纹理压缩
Beyond UV Mapping: Mesh Texture Compression via Surface-Aligned Texture Fields
浏览论文内容
中文总结 AI 辅助
针对UV图集压缩效率受限的问题，提出表面对齐纹理场TexF及GPU压缩方法3DNTC，利用稀疏体素和哈希特征实现高效压缩，在基准上优于UV方法并支持实时渲染。
中文摘要 AI 辅助
网格纹理压缩通常依赖于二维UV图集，其图表不连续性和映射开销可能限制编码效率。为应对这一挑战，我们引入了TexF，一种表面对齐的纹理场，它将纹理属性组织在源自网格表面的稀疏体素中。该表示支持高分辨率纹理，同时保留局部3D相关性以利于压缩，并支持直接表面查询。对于比特流压缩，TexF复用已建立的3D属性编解码器，体素位置从解码后的网格重建，无需单独传输。对于GPU驻留压缩，我们开发了3DNTC，它将量化哈希特征与轻量级解码器相结合，用于表面位置的随机访问重建。可微分渲染能够对体素属性和压缩神经场进行图像空间细化。在MPEG和AOM网格压缩基准上的实验表明，与代表性的基于UV的方法相比，在比特流和GPU驻留压缩方面均取得了改进的平均率失真性能。3DNTC还支持实时渲染。
英文摘要
Mesh texture compression typically relies on 2D UV atlases, whose chart discontinuities and mapping overhead can limit coding efficiency. To tackle this challenge, we introduce TexF, a surface-aligned texture field that organizes texture attributes in sparse voxels derived from the mesh surface. This representation supports high-resolution textures while preserving local 3D correlations for compression and enabling direct surface queries. For bitstream compression, TexF reuses established 3D attribute codecs, with voxel locations reconstructed from the decoded mesh without separate transmission. For GPU-resident compression, we develop 3DNTC, which combines quantized hash features with a lightweight decoder for random-access reconstruction at surface positions. Differentiable rendering enables image-space refinement of both voxel attributes and compressed neural fields. Experiments on the MPEG and AOM mesh compression benchmarks demonstrate improved average rate-distortion performance over representative UV-based methods for both bitstream and GPU-resident compression. 3DNTC also supports real-time rendering.
发表机构
- City University of Hong Kong（香港城市大学）
- Shanghai Jiao Tong University（上海交通大学）
- Texas A&M University（德克萨斯A&M大学）
机构由 AI 辅助整理，请以论文原文为准。
