Research map / 3D vision / Human pose estimation
AniMer+: Unified Pose and Shape Estimation Across Mammalia and Aves via Family-Aware Transformer
Liang An, Jin Lyu, Li Lin, Pujin Cheng, Yebin Liu, Xiaoying Tang
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 CtrlAni3D synthetic data to training (ablation) | AniMer-M · Animal3D | PA-MPJPE: 82.6 -> 80.4 | Improved |
| add CtrlAni3D to training (ablation) | AniMer-M · Animal Kingdom (OOD) | AUC: 78.5 -> 82.7 | Improved |
| add CtrlAVES3D to CUB training (ablation) | AniMer-A · Cow Bird (OOD) | AUC: 53.4 -> 65.7 | Improved |
| train with generated failure cases (no filtering) (ablation) | AniMer-M (Equidae) · Animal3D horse | PA-MPJPE: 107.9 -> 141.8 | Hurt |
| add CtrlAni3D for challenging poses (ablation) | AniMer-M · Animal Kingdom challenging subset | AUC: 80.6 -> 81.0 | Improved |
| scale CtrlAni3D size from 2.5K to 10K (ablation) | AniMer-M · Animal3D | AUC: 79.5 -> 83.5 | Improved |
| use ViT encoder instead of ResNet-152 (ablation) | AniMer-M · Animal3D | PA-MPJPE: 115.5 -> 80.4 | Improved |
| add ViTPose++ pretraining of the ViT (ablation) | AniMer-M · Animal3D | PA-MPJPE: 147.9 -> 80.4 | Improved |
| use Transformer decoder instead of MLP (ablation) | AniMer-M · Animal3D | PA-MPJPE: 83.9 -> 80.4 | Improved |
| add family supervised contrastive loss (ablation) | AniMer-M · Animal3D | PA-MPJPE: 81.3 -> 80.4 | Improved |
| add family supervised contrastive loss (ablation) | AniMer-A · CtrlAVES3D | PA-MPJPE: 72.8 -> 65.5 | Improved |
| add MoE taxa-specific layers (ablation) | AniMer+ · CUB | PCK@0.1: 53.8 -> 59.4 | Improved |
Closest papers by meaning
- SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild (NeurIPS 2026 · similarity 0.87)
- Learning the 3D Fauna of the Web (CVPR 2024 · similarity 0.87)
- Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance (NeurIPS 2025 · similarity 0.87)
- Reconstructing Animals and the Wild (CVPR 2025 · similarity 0.87)
- SAOR: Single-View Articulated Object Reconstruction (CVPR 2024 · similarity 0.87)
- Web-Scale Collection of Video Data for 4D Animal Reconstruction (NeurIPS 2025 · similarity 0.86)
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.
