Research map / 3D vision / Face and shape
ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wild
Chen Guo, Tianjian Jiang, Manuel Kaufmann, Chengwei Zheng, Julien Valentin, Jie Song, Otmar Hilliges
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 |
|---|---|---|---|
| use multi-round sampling instead of one-round sampling (min of SDFs) (ablation) | ReLoo · MonoLoose surface reconstruction | Chamfer distance (cm): 2.34 -> 1.93 | Improved |
| use multi-round sampling instead of one-round sampling (ablation) | ReLoo · MonoLoose surface reconstruction | normal consistency: 0.770 -> 0.831 | Improved |
| use multi-round sampling instead of one-round sampling (ablation) | ReLoo · MonoLoose surface reconstruction | volumetric IoU: 0.879 -> 0.881 | No clear effect |
| add virtual bone deformation for garment layer (ablation) | ReLoo · MonoLoose novel view synthesis | LPIPS (x100): 3.81 -> 3.15 | Improved |
| add virtual bone deformation for garment layer (ablation) | ReLoo · MonoLoose novel view synthesis | PSNR: 28.7 -> 29.2 | Improved |
| add virtual bone deformation for garment layer (ablation) | ReLoo · DynaCap novel view synthesis | LPIPS (x100): 1.52 -> 1.27 | Improved |
| increase number of virtual bones from 20 to 320 (ablation) | ReLoo · MonoLoose subset novel view synthesis | LPIPS | Improved |
| use layered body/garment representation with virtual bones versus single-layer methods | ReLoo vs Vid2Avatar · MonoLoose novel view synthesis | PSNR: 25.9 -> 29.2 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Vid2Avatar — Vid2Avatar: 3D Avatar Reconstruction From Videos in the Wild via Self-Supervised Scene Decomposition (CVPR 2023) · better on 5 of 5 shared results
- SelfRecon — SelfRecon: Self Reconstruction Your Digital Avatar From Monocular Video (CVPR 2022) · better on 4 of 4 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
- SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements (CVPR 2021 · similarity 0.91)
- VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift (CVPR 2024 · similarity 0.90)
- DLCA-Recon: Dynamic Loose Clothing Avatar Reconstruction from Monocular Videos (AAAI 2024 · similarity 0.90)
- TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style (CVPR 2020 · similarity 0.90)
- FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling (CVPR 2025 · similarity 0.88)
- Garment Recovery with Shape and Deformation Priors (CVPR 2024 · similarity 0.88)
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.
