TEXTRIX：面向原生纹理生成及更多应用的潜变量属性网格
TEXTRIX: Latent Attribute Grid for Native Texture Generation and Beyond
用潜空间三维属性网格 + 稀疏注意力 Diffusion Transformer 直接在体空间给 3D 模型上色，绕开多视角融合的视角不一致问题；同一架构改预测语义属性即可做 3D 部件分割，为「生成式三维表征复用为判别任务」提供了可借鉴范式。
原文依据 constructs a latent 3D attribute grid and leverages a Diffusion Transformer equipped with sparse attention
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有的三维纹理生成方法通常依赖多视角融合，常受视角间不一致与复杂表面覆盖不完整的制约，限制了生成内容的保真度与完整性。为克服这些挑战，我们提出 TEXTRIX，一个原生三维属性生成框架，用于高保真纹理合成以及精确三维部件分割等下游应用。该方法构建潜变量三维属性网格，并利用配备稀疏注意力的扩散 Transformer，从而能够在体空间中直接为三维模型着色，从根本上规避多视角融合的局限。基于这一原生表示，该框架通过训练同一架构在网格上预测语义属性，自然地扩展到高精度三维分割。大量实验表明，该方法在两个任务上均达到最优性能，可生成无缝、高保真的纹理，并实现边界精确的三维部件分割。
英文原文摘要 1048 字符
Prevailing 3D texture generation methods, which often rely on multi-view fusion, are frequently hindered by inter-view inconsistencies and incomplete coverage of complex surfaces, limiting the fidelity and completeness of the generated content. To overcome these challenges, we introduce TEXTRIX, a native 3D attribute generation framework for high-fidelity texture synthesis and downstream applications such as precise 3D part segmentation. Our approach constructs a latent 3D attribute grid and leverages a Diffusion Transformer equipped with sparse attention, enabling direct coloring of 3D models in volumetric space and fundamentally avoiding the limitations of multi-view fusion. Built upon this native representation, the framework naturally extends to high-precision 3D segmentation by training the same architecture to predict semantic attributes on the grid. Extensive experiments demonstrate state-of-the-art performance on both tasks, producing seamless, high-fidelity textures and accurate 3D part segmentation with precise boundaries.