Research map / 3D vision / Human pose estimation
Multi-Person 3D Motion Prediction with Multi-Range Transformers
Jiashun Wang, Huazhe Xu, Medhini Narasimhan, Xiaolong Wang
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 local-range encoder (ablation) | Multi-Range Transformers · CMU-Mocap 3s | MPJPE: 2.99 -> 2.18 | Improved |
| add global-range encoder (ablation) | Multi-Range Transformers · CMU-Mocap 3s | MPJPE: 2.50 -> 2.18 | Improved |
| add motion discriminator (adversarial training) (ablation) | Multi-Range Transformers · CMU-Mocap 3s | MPJPE: 2.57 -> 2.18 | Improved |
| add spatial positional encoding (ablation) | Multi-Range Transformers · Mix2 3s | MPJPE: 2.92 -> 2.82 | Improved |
| add spatial positional encoding (ablation) | Multi-Range Transformers · MuPoTS-3D 2s | MPJPE: 1.51 -> 1.59 | Hurt |
| add local-range encoder (ablation) | Multi-Range Transformers · 3DPW 3s | MPJPE: 7.75 -> 7.83 | Hurt |
| add global-range encoder (ablation) | Multi-Range Transformers · MuPoTS-3D 3s | MPJPE: 2.50 -> 2.22 | Improved |
| use single pose as decoder query instead of a sequence (ablation) | Multi-Range Transformers · CMU-Mocap | MPJPE | Improved |
| progressively growing input length instead of fixed one-second input (ablation) | Multi-Range Transformers · CMU-Mocap | MPJPE | Improved |
| use 3 Transformer layers instead of 1, 6 or 9 (ablation) | Multi-Range Transformers · CMU-Mocap | MPJPE | Improved |
| apply DCT only to local encoder input rather than all inputs or no DCT (ablation) | Multi-Range Transformers · CMU-Mocap | MPJPE | Improved |
Closest papers by meaning
- Stochastic Multi-Person 3D Motion Forecasting (ICLR 2023 · similarity 0.90)
- Efficient Multi-Person Motion Prediction by Lightweight Spatial and Temporal Interactions (ICCV 2025 · similarity 0.90)
- SimpliHuMoN: Simplifying Human Motion Prediction (NeurIPS 2026 · similarity 0.88)
- Social-Transmotion: Promptable Human Trajectory Prediction (ICLR 2024 · similarity 0.87)
- Motion Diversification Networks (CVPR 2024 · similarity 0.86)
- Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning (CVPR 2024 · 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.
