Research map / 3D vision / Face and shape
UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation
Shenhan Qian, Jiale Xu, Ziwei Liu, Liqian Ma, Shenghua Gao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add adjacent part seaming (APS) (ablation) | UNIF · unseen pose, qualitative | visual quality | Improved |
| add bone limit loss (ablation) | UNIF · partition at early training, qualitative | part division | Improved |
| add section normal loss (ablation) | UNIF · partition at early training, qualitative | part division | Improved |
| add minimal perimeter loss (ablation) | UNIF · partition at early training, qualitative | extra surfaces | Improved |
| UNIF instead of SNARF | clothed human reconstruction · CAPE extrapolation test | Chamfer distance (CD): 29.34 -> 6.64 | Improved |
| UNIF instead of NASA | part-based reconstruction · CAPE extrapolation test | Chamfer distance (CD): 98.23 -> 8.06 | Improved |
| UNIF instead of SCANimate/SNARF | ClothSeq interpolation · ClothSeq interpolation test | Chamfer distance (CD): 8.81 -> 8.89 (JS) | Mixed |
| use Fourier features | UNIF · training initialization | initialization / extra surfaces | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SCANimate — SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks (CVPR 2021) · better on 8 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing (ICCV 2021 · similarity 0.88)
- Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction (ECCV 2020 · similarity 0.88)
- ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wild (ECCV 2024 · similarity 0.88)
- REACTO: Reconstructing Articulated Objects from a Single Video (CVPR 2024 · similarity 0.87)
- DLCA-Recon: Dynamic Loose Clothing Avatar Reconstruction from Monocular Videos (AAAI 2024 · similarity 0.87)
- MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
