Research map / 3D vision / Face and shape
Human Mesh Modeling for Anny Body
Romain Brégier, Guénolé Fiche, Matthieu Armando, Laura Bravo-Sánchez, Thomas Lucas, Philippe Weinzaepfel, Grégory Rogez, Fabien Baradel
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 |
|---|---|---|---|
| swap SMPL-X for Anny body model (ablation) | HMR2.0 (BEDLAM) · 3DPW | PA-MPJPE: 52.0 -> 49.4 | Improved |
| swap SMPL-X for Anny body model (ablation) | HMR2.0 (BEDLAM) · 3DPW | MPJPE: 86.0 -> 86.5 | No clear effect |
| swap SMPL-X for Anny body model (ablation) | HMR2.0 (BEDLAM) · EHF | PVE: 76.4 -> 65.5 | Improved |
| swap SMPL-X for Anny body model (ablation) | Multi-HMR (BEDLAM) · EHF | PVE: 66.2 -> 68.6 | Hurt |
| swap SMPL-X for Anny body model (ablation) | Multi-HMR (BEDLAM) · 3DPW | PA-MPJPE: 56.3 -> 54.3 | Improved |
| swap SMPL-X for Anny body model (ablation) | Multi-HMR (BEDLAM pretrain) · AGORA-Kids | PVE: 186.0 -> 175.6 | Improved |
| replace BEDLAM with Anny-One pretraining (ablation) | Multi-HMR + Anny · AGORA-Kids | PVE: 175.6 -> 113.9 | Improved |
| replace BEDLAM with Anny-One pretraining (ablation) | Multi-HMR + Anny · AGORA-All | PVE: 136.7 -> 118.5 | Improved |
| use Anny rather than SMPL-X when training on AGORA (ablation) | Multi-HMR · AGORA-Kids | PVE: 99.5 -> 79.0 | Improved |
| use Anny rather than SMPL-X+A when training on AGORA (ablation) | Multi-HMR · AGORA-Kids | PVE: 80.8 -> 79.0 | Improved |
| pretrain on Anny-One with Anny then finetune on AGORA vs BEDLAM + SMPL-X+A (ablation) | Multi-HMR · AGORA-All | PVE: 76.6 -> 72.8 | Improved |
| add Anny to Multi-HMR trained on large data mix | Multi-HMR · CMU-Toddler | MPJPE: 153.6 -> 102.1 | Improved |
Closest papers by meaning
- Accurate 3D Body Shape Regression Using Metric and Semantic Attributes (CVPR 2022 · similarity 0.89)
- ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling (ICCV 2025 · similarity 0.89)
- SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling (ICCV 2023 · similarity 0.87)
- SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion (CVPR 2024 · similarity 0.86)
- GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data (NeurIPS 2025 · similarity 0.85)
- HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion (ICLR 2024 · similarity 0.85)
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.
