Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinates
Li, Ren Cao, Cong Dumery, Corentin You, Yingxuan Li, Hao Fua, Pascal V
Li, Ren
Cao, Cong
Dumery, Corentin
You, Yingxuan
Li, Hao
Fua, Pascal V
Supervisor
Department
Computer Vision
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
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.
Citation
R. Li, C. Cao, C. Dumery, Y. You, H. Li, and P. Fua, “Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinates,” pp. 1–11, Aug. 2025, doi: 10.1145/3721238.3730651
Source
Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers
Conference
SIGGRAPH 2025 Conference Papers
Keywords
3d Garment Reconstruction, Diffusion Models, Image Based Modeling, 3d Reconstruction, Clothes, Geometry, Hosiery Manufacture, Image Reconstruction, Interactive Computer Graphics, Mapping, Mixed Reality, Textiles, Textures, Three Dimensional Computer Graphics, 3d Garment Reconstruction, 3d Garments, Diffusion Mappings, Diffusion Model, High-fidelity, Human Bodies, Image-based Models, Novel Methods, Virtual Try-on, Diffusion
Subjects
Source
SIGGRAPH 2025 Conference Papers
Publisher
Association for Computing Machinery