Research map / 3D vision / Human pose estimation
Event-based Head Pose Estimation: Benchmark and Method
Jiahui Yuan, Hebei Li, Yansong Peng, Jin Wang, Yuheng Jiang, Yueyi Zhang, Xiaoyan Sun
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 the ESTF module (spatial-temporal fusion of voxel grid) (ablation) | EV-HPE · Prophesee-HP | Euler MAE: 6.52 -> 6.01 | Improved |
| add the EMPA attention module (ablation) | EV-HPE · Prophesee-HP | Euler MAE: 6.55 -> 6.01 | Improved |
| add the angle loss to the geodesic loss (ablation) | EV-HPE · Prophesee-HP | Euler MAE: 6.14 -> 6.01 | Improved |
| increase number of stacked EMPA blocks from 0 to 4 (ablation) | EV-HPE · Prophesee-HP | Euler MAE: 6.55 -> 6.01 | Improved |
| use event streams instead of RGB frames as input for existing HPE methods | 6DRepNet · Davis-HP (40ms) | Euler MAE: 9.64 -> 7.32 | Improved |
| use event streams instead of RGB frames as input | HopeNet · Davis-HP (40ms) | Euler MAE: 11.91 -> 8.46 | Improved |
| use EV-HPE instead of best baseline 6DRepNet on event input | Prophesee-HP · Prophesee-HP (10ms) | Euler MAE: 6.85 -> 6.01 | Improved |
| use EV-HPE instead of 6DRepNet on event input | Davis-HP · Davis-HP (10ms) | Euler MAE: 7.28 -> 6.49 | 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.
- HopeNet — HOPE-Net: A Graph-Based Model for Hand-Object Pose Estimation (CVPR 2020) · 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
- EventHPE: Event-Based 3D Human Pose and Shape Estimation (ICCV 2021 · similarity 0.89)
- TokenHPE: Learning Orientation Tokens for Efficient Head Pose Estimation via Transformers (CVPR 2023 · similarity 0.87)
- EventEgo3D++: 3D Human Motion Capture from A Head-Mounted Event Camera (IJCV 2025 · similarity 0.86)
- EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision (AAAI 2025 · similarity 0.85)
- A Benchmark Dataset for Event-Guided Human Pose Estimation and Tracking in Extreme Conditions (NeurIPS 2024 · similarity 0.85)
- A Simple and Effective Point-based Network for Event Camera 6-DOFs Pose Relocalization (CVPR 2024 · similarity 0.84)
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.
