YuliangXiu/ICON
CVPR 2022 project that reconstructs 3D clothed human meshes from single RGB images using implicit neural representations and SMPL body models.
Not currently ranked — collecting fresh signals.
star history
ICON (Implicit Clothed humans Obtained from Normals) is a computer vision research project that reconstructs detailed 3D human meshes with clothing from single-view images. It leverages implicit neural functions combined with normal map estimation and SMPL/SMPLX body models to generate animatable avatars. The method uses PyTorch and PyTorch Lightning for training and inference, and is designed for applications in computer graphics, virtual humans, and the metaverse.
Frequently asked
- What is YuliangXiu/ICON?
- CVPR 2022 project that reconstructs 3D clothed human meshes from single RGB images using implicit neural representations and SMPL body models.
- Is ICON open source?
- Yes — YuliangXiu/ICON is an open-source project tracked on heatdrop.
- What language is ICON written in?
- YuliangXiu/ICON is primarily written in Python.
- How popular is ICON?
- YuliangXiu/ICON has 1.7k stars on GitHub.
- Where can I find ICON?
- YuliangXiu/ICON is on GitHub at https://github.com/YuliangXiu/ICON.