Research map / 3D vision / Human pose estimation
Forecasting Human Dynamics From Static Images
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 recurrent 3D-PFNet instead of NN-oracle forecasting | 2D pose forecasting · Penn Action, timestep 2 | PCK@0.05 (%): 44.1 -> 60.0 | Helped |
| Use recurrent 3D-PFNet instead of NN-oracle forecasting | 2D pose forecasting · Penn Action, timestep 16 | PCK@0.05 (%): 29.3 -> 43.3 | Helped |
| Filter nearest-neighbor candidates using scene context | NN-all · Penn Action, later timesteps | PCK@0.05 (%): 43.2 -> 43.3 | Helped |
| Filter nearest-neighbor candidates to the ground-truth action category | NN-CaffeNet · Penn Action, later timesteps | PCK@0.05 (%): 43.3 -> 44.1 | Helped |
| Regress 3D joints from heatmaps with the learned bottom-up converter instead of Convex | 3D pose recovery · Human3.6M | MPJPE (mm), Avg: 158.6 -> 87.6 | Helped |
| Regress 3D joints with the learned converter instead of SMPLify | 3D pose recovery · Human3.6M | MPJPE (mm), Avg: 154.9 -> 87.6 | Helped |
Closest papers by meaning
- FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations (CVPR 2024 · similarity 0.90)
- Learning 3D Human Dynamics From Video (CVPR 2019 · similarity 0.90)
- Expressive Forecasting of 3D Whole-Body Human Motions (AAAI 2024 · similarity 0.88)
- Forecasting of 3D Whole-body Human Poses with Grasping Objects (CVPR 2024 · similarity 0.88)
- MotionMap: Representing Multimodality in Human Pose Forecasting (CVPR 2025 · similarity 0.87)
- VideoMDM: Towards 3D Human Motion Generation From 2D Supervision (NeurIPS 2026 · 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.