从单张图重建3D衣物，用扩散模型学形状先验。
Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinates
- 用扩散模型在UV空间学习衣物形状先验
- 真实图像上重建效果优于现有方法，细节丰富
- 适合虚拟试衣、服装重定位等应用
从图像重建3D着装人体是虚拟试穿、角色创建和混合现实应用的基础。尽管人体恢复技术已有进展，但松身衣物的精确几何重建仍是挑战。本文提出一种新方法，通过隐式缝制模式（ISP）结合生成式扩散模型，在2D UV空间学习丰富的衣物形状先验。关键创新在于建立2D图像像素、UV图案坐标与3D几何间的对应关系，实现3D衣物网格与对应2D图案的联合优化，使学习到的先验与图像观测对齐。模型仅在合成布料数据上训练，却能有效泛化至真实图像，在紧身与松身衣物上均优于现有方法。重建衣物保持物理合理性并捕捉精细几何细节，支持服装重定位与纹理操作等下游任务。
原文摘要 · Abstract (English)
Reconstructing 3D clothed humans from images is fundamental to applications like virtual try-on, avatar creation, and mixed reality. While recent advances have enhanced human body recovery, accurate reconstruction of garment geometry -- especially for loose-fitting clothing -- remains an open challenge. We present a novel method for high-fidelity 3D garment reconstruction from single images that bridges 2D and 3D representations. Our approach combines Implicit Sewing Patterns (ISP) with a generative diffusion model to learn rich garment shape priors in a 2D UV space. A key innovation is our mapping model that establishes correspondences between 2D image pixels, UV pattern coordinates, and 3D geometry, enabling joint optimization of both 3D garment meshes and the corresponding 2D patterns by aligning learned priors with image observations. Despite training exclusively on synthetically simulated cloth data, our method generalizes effectively to real-world images, outperforming existing approaches on both tight- and loose-fitting garments. The reconstructed garments maintain physical plausibility while capturing fine geometric details, enabling downstream applications including garment retargeting and texture manipulation.
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。