Research map / 3D vision / Human pose estimation
Expanding mmWave Datasets for Human Pose Estimation with Unlabeled Data and LiDAR Datasets
Zhuoxuan Peng, Boan Zhu, Xingjian Zhang, Wenying Li, S.-H. Gary Chan
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 LiDAR-to-mmWave point cloud conversion (EMDUL-PCC) to 10% labeled data (ablation) | P4T · MM-Fi -> mmBody | MPJPE: 20.78 -> 15.22 | Improved |
| add pseudo-labeled unlabeled mmWave data only (EMDUL-PL) (ablation) | P4T · MM-Fi -> mmBody | MPJPE: 20.78 -> 22.90 | Mixed |
| add pseudo-labeling to LiDAR-converted data (full EMDUL) (ablation) | P4T · MM-Fi -> mmBody | MPJPE: 15.22 -> 14.89 | Improved |
| use EMDUL instead of Mean Teacher pseudo-labeling with the same data | P4T · mmBody -> MM-Fi | MPJPE: 31.51 -> 24.01 | Improved |
| use unsupervised temporal consistency loss (DCL+SCL) for estimator (ablation) | EMDUL · MM-Fi + HmPEAR -> mmBody | MPJPE: 15.12 -> 14.89 | Improved |
| use only DCL or only SCL (ablation) | EMDUL · MM-Fi + HmPEAR -> mmBody | MPJPE: 15.12 -> 15.35 / 15.53 | Hurt |
| add flow-based point filtering to point cloud conversion (ablation) | EMDUL-PCC · MM-Fi + HmPEAR -> mmBody | realism and MPJPE: 43.06 -> 60.46 | Improved |
| use height instead of Doppler speed as point feature (ablation) | P4T · MM-Fi -> mmBody | MPJPE: 25.15 -> 19.68 | Improved |
| use EMDUL at 50% labeled ratio instead of Mean Teacher | P4T · MM-Fi -> MM-Fi | MPJPE: 8.25 -> 8.15 | No clear effect |
| use EMDUL at 1% labeled ratio instead of Mean Teacher | P4T · MM-Fi -> MM-Fi | MPJPE: 18.40 -> 14.77 | Improved |
Closest papers by meaning
- Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimation (AAAI 2025 · similarity 0.86)
- MVDoppler-Pose: Multi-Modal Multi-View mmWave Sensing for Long-Distance Self-Occluded Human Walking Pose Estimation (CVPR 2025 · similarity 0.84)
- Neighborhood-Enhanced 3D Human Pose Estimation with Monocular LiDAR in Long-Range Outdoor Scenes (AAAI 2024 · similarity 0.83)
- LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment (CVPR 2024 · similarity 0.83)
- MITO: A Millimeter-Wave Dataset and Simulator for Non-Line-of-Sight Perception (NeurIPS 2026 · similarity 0.83)
- LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes (CVPR 2024 · similarity 0.82)
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.
