Research map / 3D vision / Human pose estimation
AvatarPose: Avatar-guided 3D Pose Estimation of Close Human Interaction from Sparse Multi-view Videos
Feichi Lu, Zijian Dong, 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 avatar-based color and silhouette rendering loss instead of SMPL fitting to 2D joints (ablation) | AvatarPose · Hi4D | MPJPE (mm): 40.41 -> 29.37 | Improved |
| add RGB rendering loss (ablation) | AvatarPose · Hi4D | MPJPE (mm): 78.40 -> 29.37 | Improved |
| add mask (silhouette) loss (ablation) | AvatarPose · Hi4D | MPJPE (mm): 31.00 -> 29.37 | Improved |
| alternate avatar refinement and pose optimization instead of joint optimization (ablation) | AvatarPose · Hi4D | MPJPE (mm): 66.04 -> 29.37 | Improved |
| add avatar-based collision (penetration) loss (ablation) | AvatarPose · Hi4D | interpenetration (qualitative) | Improved |
| use AvatarPose instead of 4DAssociation | multi-view pose estimation · Hi4D (8 views) | MPJPE (mm): 41.29 -> 32.10 | Improved |
| use AvatarPose instead of MVPose | multi-view pose estimation · CHI3D (4 views) | MPJPE (mm): 34.05 -> 32.98 | Improved |
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.
- Faster VoxelPose — Faster VoxelPose: Real-Time 3D Human Pose Estimation by Orthographic Projection (ECCV 2022) · better on 1 of 1 shared result
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
- GeoAvatar: Geometrically-Consistent Multi-Person Avatar Reconstruction from Sparse Multi-View Videos (CVPR 2025 · similarity 0.90)
- Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior (CVPR 2025 · similarity 0.88)
- NoPo-Avatar: Generalizable and Animatable Avatars from Sparse Inputs without Human Poses (NeurIPS 2025 · similarity 0.88)
- FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images (CVPR 2025 · similarity 0.87)
- RAM-Avatar: Real-time Photo-Realistic Avatar from Monocular Videos with Full-body Control (CVPR 2024 · similarity 0.87)
- 3D²-Actor: Learning Pose-Conditioned 3D-Aware Denoiser for Realistic Gaussian Avatar Modeling (AAAI 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.
