发表机构
Jilin University; Zhejiang University; North China University of Technology（吉林大学; 浙江大学; 北方工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究旨在弥合真实图像与合成3D表面的外观差距，提出RealSkin自监督框架，通过空间引导配准算法和谱感知神经伴随网络，在谱域优化对应，实验表明该方法在真实到合成场景中性能达最优。
AI 中文摘要
创建逼真的3D资产需要弥合现实世界观察与合成模型之间的外观差距。一种有前景的方法是将视觉属性从真实图像转移到合成3D表面。传统方法在分辨率不匹配和点对应固有的离散性方面存在困难。相比之下，分辨率鲁棒的功能映射可实现平滑属性传播，但依赖近等距假设和拓扑一致性。为解决这些限制，我们提出RealSkin，一个在学习的谱域中进行对应优化的自监督框架，由空间对应引导。我们首先引入一种空间引导的配准算法，在严重拓扑差异下建立粗略对应。为放宽严格的等距假设并处理部分对应，我们进一步设计了一个谱感知神经伴随网络，将部分对应纳入神经函数空间并对非等距残差建模以进行对应细化。实验结果表明，我们的方法在具有挑战性的真实到合成场景中实现了当前最优性能。代码将公开发布。
英文摘要
Creating photorealistic 3D assets requires bridging the appearance gap between real-world observations and synthetic models. A promising approach is to transfer visual attributes from real images onto synthetic 3D surfaces. Traditional methods struggle with resolution mismatch and the inherent discreteness of point correspondences. In contrast, resolution-robust functional maps enable smooth attribute propagation but rely on near-isometry assumptions and topological consistency. To address these limitations, we propose RealSkin, a self-supervised framework that performs correspondence optimization in a learned spectral domain, guided by spatial correspondences. We first introduce a spatial-guided registration algorithm to establish coarse correspondences under severe topological discrepancies. To relax strict isometric assumptions and handle partial correspondences, we further design a spectral-aware neural adjoint network that incorporates partial correspondences into a neural function space and models non-isometric residuals for correspondence refinement. Experimental results demonstrate that our method achieves state-of-the-art performance on challenging real-to-synthetic scenarios. The code will be publicly released.
