NI-Tex：非等距的基于图像服装纹理生成
NI-Tex: Non-isometric Image-based Garment Texture Generation
面向非等距图像-网格对的前馈双分支 PBR 材质生成，配合不确定性引导的视角选择与重加权迭代烘焙，可复用于任意 3D 资产从单张野外图像反推无缝 PBR 纹理的流程。
原文依据 we propose an iterative baking method via uncertainty-guided view selection and reweighting that fuses multi-view predictions into seamless, production-ready PBR textures
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工业级三维服装网格已覆盖大多数真实世界的服装几何形态，但其纹理多样性仍然有限。为获得更真实的纹理，生成式方法常被用于从大量野外图像中提取基于物理的渲染（PBR）纹理与材质，并将其投影回服装网格。然而，多数以图像为条件的纹理生成方法要求输入图像与输入三维网格之间具有严格的拓扑一致性，或依赖精确的网格变形来匹配图像姿态，这显著制约了纹理生成的质量与灵活性。为应对非等距的基于图像服装纹理生成这一难题，我们构建了 3D Garment Videos，这是一个经物理模拟、以服装为中心的数据集，在多样形变下提供一致的几何与材质监督，从而支持稳健的跨姿态纹理学习。我们进一步采用 Nano Banana 进行高质量的非等距图像编辑，在非等距的图像-几何对之间实现可靠的跨拓扑纹理生成。最后，我们提出一种迭代烘焙方法，通过不确定性引导的视角选择与重加权，将多视角预测融合为无缝的、可直接用于生产的 PBR 纹理。通过大量实验，我们证明所提出的前馈双分支架构能够生成多样且空间对齐的 PBR 材质，适用于工业级三维服装设计。
英文原文摘要 1497 字符
Existing industrial 3D garment meshes already cover most real-world clothing geometries, yet their texture diversity remains limited. To acquire more realistic textures, generative methods are often used to extract Physically-based Rendering (PBR) textures and materials from large collections of wild images and project them back onto garment meshes. However, most image-conditioned texture generation approaches require strict topological consistency between the input image and the input 3D mesh, or rely on accurate mesh deformation to match to the image poses, which significantly constrains the texture generation quality and flexibility.To address the challenging problem of non-isometric image-based garment texture generation, we construct 3D Garment Videos, a physically simulated, garment-centric dataset that provides consistent geometry and material supervision across diverse deformations, enabling robust cross-pose texture learning. We further employ Nano Banana for high-quality non-isometric image editing, achieving reliable cross-topology texture generation between non-isometric image-geometry pairs. Finally, we propose an iterative baking method via uncertainty-guided view selection and reweighting that fuses multi-view predictions into seamless, production-ready PBR textures. Through extensive experiments, we demonstrate that our feedforward dual-branch architecture generates versatile and spatially aligned PBR materials suitable for industry-level 3D garment design.