Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinates
This work addresses the problem of accurate 3D garment reconstruction for applications like virtual try-on and avatar creation, representing an incremental improvement over prior methods.
The paper tackles the challenge of reconstructing 3D garments from single images, particularly for loose-fitting clothing, by introducing a method that combines Implicit Sewing Patterns with a diffusion model to learn shape priors in UV space, resulting in high-fidelity reconstructions that outperform existing approaches on both tight- and loose-fitting garments.
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.