Research map / 3D vision / Human pose estimation
EventHPE: Event-Based 3D Human Pose and Shape Estimation
Shihao Zou, Chuan Guo, Xinxin Zuo, Sen Wang, Pengyu Wang, Xiaoqin Hu, Shoushun Chen, Minglun Gong, Li Cheng
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 inferred optical flow as extra input | DHP19 pose network · DHP19 | MPJPE (mm): 80.08 -> 76.76 | Improved |
| add inferred optical flow as extra input | DHP19 pose network · DHP19 | PA-MPJPE (mm): 74.55 -> 71.68 | Improved |
| add inferred optical flow as extra input | DHP19 pose network · DHP19 | PEL-MPJPE (mm): 131.73 -> 130.37 | No clear effect |
| add inferred optical flow as extra input | DHP19 pose network · DHP19 | PCKh@0.5: 0.80 -> 0.82 | Improved |
| add optical flow input and flow coherence loss (ablation) | EventHPE · MMHPSD | PA-MPJPE (mm): 49.43 -> 43.90 | Improved |
| add optical flow input and flow coherence loss (ablation) | EventHPE · MMHPSD | PVE (mm): 59.77 -> 53.90 | Improved |
| add flow coherence loss on top of flow input (ablation) | EventHPE · MMHPSD | PA-MPJPE (mm): 47.36 -> 43.90 | Improved |
| add flow coherence loss on top of flow input (ablation) | EventHPE · MMHPSD | PVE (mm): 56.58 -> 53.90 | Improved |
| use geodesic SO(3) distance instead of Euclidean for pose loss (ablation) | EventHPE · MMHPSD | PA-MPJPE (mm): 49.02 -> 43.90 | Improved |
| use geodesic SO(3) distance instead of Euclidean for pose loss (ablation) | EventHPE · MMHPSD | PVE (mm): 59.84 -> 53.90 | Improved |
| add 3D and 2D joint supervision (ablation) | EventHPE · MMHPSD | PA-MPJPE (mm): 44.59 -> 43.90 | Improved |
| add 3D and 2D joint supervision (ablation) | EventHPE · MMHPSD | MPJPE (mm): 73.79 -> 71.79 | Improved |
Later papers that compared with this method
2 later accepted papers report EventHPE as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Continuous-Time Human Motion Field from Event Cameras (ICCV 2025 · better on 6 of 6 shared results)
- RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method (CVPR 2024 · better on 1 of 1 shared result)
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.
- VIBE — VIBE: Video Inference for Human Body Pose and Shape Estimation (CVPR 2020) · better on 3 of 3 shared results
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
- Event-based Head Pose Estimation: Benchmark and Method (ECCV 2024 · similarity 0.89)
- EventCap: Monocular 3D Capture of High-Speed Human Motions Using an Event Camera (CVPR 2020 · similarity 0.88)
- EventEgo3D++: 3D Human Motion Capture from A Head-Mounted Event Camera (IJCV 2025 · similarity 0.87)
- Continuous-Time Human Motion Field from Event Cameras (ICCV 2025 · similarity 0.87)
- EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams (CVPR 2024 · similarity 0.86)
- Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation From Monocular Video (CVPR 2022 · 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.
