OMGTex：无需几何引导的单阶段多风格人脸纹理重建
OMGTex: One-stage Multi-style Facial Texture Reconstruction without Geometry Guidance
把「2D 人脸图像→可编辑 UV 纹理」做成无几何先验的单阶段扩散流程，并用推理时梯度引导修正 UV 错位，这对做人脸重建/纹理生成的人提供了一个绕开 3DMM 拟合误差、且支持区域级语义编辑的替代方案。
原文依据 a geometry-free pipeline that directly maps a 2D face image to its corresponding editable UV texture
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 OMGTex，一个端到端的扩散框架，用于从多风格人脸图像重建高质量且可编辑的人脸 UV 纹理。现有纹理重建方法面临两大局限：(1) 依赖 3D 几何先验而导致的脆弱性，这类先验难以准确估计，在人脸遮挡或风格化域中尤为如此；(2) 缺乏语义解耦，阻碍了区域特定的纹理编辑与风格迁移。本工作同时应对这两项挑战。我们的核心创新是一个无几何流程，直接将 2D 人脸图像映射为其对应的可编辑 UV 纹理。我们引入两项关键技术：第一，针对扩散生成中常见的 UV 错位问题，我们在推理阶段引入梯度引导的细化策略，显式修正结构一致性。第二，我们利用扩散模型固有的语义分布能力，并设计一种新的训练范式以强化这一倾向，从而实现人脸纹理的语义感知编辑。此外，为缓解多风格纹理重建中的数据稀缺问题，我们构建了 CANVAS，这是首个覆盖真实域与多样风格化域的综合性成对纹理重建数据集。据我们所知，OMGTex 是首个无几何推理框架，能够在多样域中实现鲁棒、风格一致且可编辑的人脸纹理重建。我们的方法在人脸纹理基准上取得了最优性能。代码与预训练模型权重将公开发布。
英文原文摘要 1644 字符
We propose OMGTex, an end-to-end diffusion-based framework for reconstructing high-quality and editable facial UV textures from multi-style facial images. Existing texture reconstruction methods face two major limitations: (1) Fragility due to reliance on 3D geometry priors, which are difficult to estimate accurately, especially under facial occlusions or in stylized domains; and (2) A lack of semantic disentanglement, inhibiting region-specific texture editing and style transfer. Our work addresses both challenges simultaneously.Our core innovation is a geometry-free pipeline that directly maps a 2D face image to its corresponding editable UV texture. We introduce two key techniques: First, to address the challenge of UV misalignment common in diffusion generation, we introduce a gradient-guided refinement strategy at inference time, which explicitly corrects structural consistency. Second, we leverage the inherent semantic distribution capability of diffusion models and design a novel training paradigm to enhance this tendency, enabling semantic-aware editing of facial texture. Furthermore, to address the data scarcity in multi-style texture reconstruction, we construct CANVAS, the first comprehensive paired texture reconstruction dataset covering realistic and diverse stylized domains.To the best of our knowledge, OMGTex is the first geometry-free inference framework that achieves robust, style-consistent, and editable facial texture reconstruction across diverse domains. Our method achieves state-of-the-art performance on facial texture benchmarks. Codes and the pretrained model weights will be publicly released.