We present MatAtlas, a method for consistent text-guided 3D model texturing. Following recent progress we leverage a large scale text-to-image generation model (e.g., Stable Diffusion) as a prior to texture a 3D model. We carefully design an RGB texturing pipeline that leverages a grid pattern diffusion, driven by depth and edges. By proposing a multi-step texture refinement process, we significantly improve the quality and 3D consistency of the texturing output. To further address the problem of baked-in lighting, we move beyond RGB colors and pursue assigning parametric materials to the assets. Given the high-quality initial RGB texture, we propose a novel material retrieval method capitalized on Large Language Models (LLM), enabling editabiliy and relightability. We evaluate our method on a wide variety of geometries and show that our method significantly outperform prior arts. We also analyze the role of each component through a detailed ablation study.

翻译：我们提出MatAtlas，一种用于文本引导下三维模型一致性纹理生成的方法。借鉴近期进展，我们利用大规模文本到图像生成模型（如Stable Diffusion）作为先验信息来为三维模型生成纹理。我们精心设计了一套基于深度与边缘信息的网格图案扩散RGB纹理管线。通过提出多步纹理精炼流程，我们显著提升了纹理输出的质量与三维一致性。为消除固化光照问题，我们进一步突破RGB色彩限制，致力于为资产分配参数化材质。基于高质量初始RGB纹理，我们提出一种利用大型语言模型（LLM）的新型材质检索方法，实现了材质的可编辑性与可重照明性。我们在多种几何体上评估该方法，结果表明其显著优于现有技术。通过详细的消融研究，我们分析了各组件的作用。