OMGTex: 无需几何引导的一阶段多风格面部纹理重建
OMGTex: One-stage Multi-style Facial Texture Reconstruction without Geometry Guidance
AI总结：
提出OMGTex，一种端到端的扩散框架，无需3D几何先验，直接从多风格面部图像重建高质量、可编辑的UV纹理，通过梯度引导推理和语义感知训练实现鲁棒重建与编辑。
摘要：
我们提出OMGTex，一种端到端的基于扩散的框架，用于从多风格面部图像重建高质量且可编辑的面部UV纹理。现有的纹理重建方法面临两个主要限制：(1) 依赖于难以准确估计的3D几何先验，尤其是在面部遮挡或风格化域中，导致脆弱性；(2) 缺乏语义解耦，阻碍了区域特定的纹理编辑和风格迁移。我们的工作同时解决了这两个挑战。 我们的核心创新是一个无几何的流水线，直接将2D面部图像映射到其对应的可编辑UV纹理。我们引入了两种关键技术：首先，为了解决扩散生成中常见的UV错位问题，我们引入了一种推理时的梯度引导细化策略，显式校正结构一致性。其次，我们利用扩散模型固有的语义分布能力，设计了一种新颖的训练范式来增强这种倾向，从而实现面部纹理的语义感知编辑。此外，为了解决多风格纹理重建中的数据稀缺问题，我们构建了CANVAS，这是第一个涵盖真实和多样化风格化领域的全面配对纹理重建数据集。 据我们所知，OMGTex是第一个无几何推理框架，能够在不同领域实现鲁棒、风格一致且可编辑的面部纹理重建。我们的方法在多个面部纹理基准上达到了最先进的性能。
英文摘要：
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 multiple facial texture benchmarks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
