直接在3D网格上生成纹理，解决多视角图像映射的几何不一致问题。
DoubleDiffusion: Combining Heat Diffusion with Denoising Diffusion for Texture Generation on 3D Meshes
- 用热扩散传播网格表面特征，不受线框布局影响。
- 相比传统方法，生成效率显著提升。
- 适合需要高质量3D纹理生成的研究与应用
本文针对3D网格资产的纹理生成问题提出新方法。现有方法通常依赖图像扩散模型生成多视角图像，再将其投影到网格表面形成单一纹理，但因多视角图像与三维空间之间的差异，易产生几何不一致、可见性遮挡和烘焙伪影等问题。为此，本文提出一种直接在3D网格上生成纹理的新方法。该方法利用热耗散扩散作为高效算子，在网格几何表面上传播特征，且对线框布局不敏感。通过将该技术融入生成式扩散流程，显著提升了纹理生成效率。本文将该方法命名为DoubleDiffusion，因其结合了热扩散与去噪扩散，实现了在3D网格表面的原生生成学习。
原文摘要 · Abstract (English)
This paper addresses the problem of generating textures for 3D mesh assets. Existing approaches often rely on image diffusion models to generate multi-view image observations, which are then transformed onto the mesh surface to produce a single texture. However, due to the gap between multi-view images and 3D space, such process is susceptible to arange of issues such as geometric inconsistencies, visibility occlusion, and baking artifacts. To overcome this problem, we propose a novel approach that directly generates texture on 3D meshes. Our approach leverages heat dissipation diffusion, which serves as an efficient operator that propagates features on the geometric surface of a mesh, while remaining insensitive to the specific layout of the wireframe. By integrating this technique into a generative diffusion pipeline, we significantly improve the efficiency of texture generation compared to existing texture generation methods. We term our approach DoubleDiffusion, as it combines heat dissipation diffusion with denoising diffusion to enable native generative learning on 3D mesh surfaces.
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。