Research map / 3D vision / Human pose estimation
Bezier Degradation Modeling for LiDAR-based Human Motion Capture
Xiaoqi An, Lin Zhao, Jun Li, Chen Gong, Jian Yang
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 Trajectory-Aware Degradation (TAD) to the 3-level Bezier schedule (ablation) | BMLiCap · LiDARHuman26M | MPJPE: 67.9 -> 66.8 | Improved |
| add TAD with only 2 levels (ablation) | BMLiCap · LiDARHuman26M | Accel Err: 28.8 -> 28.9 | No clear effect |
| use Bezier+TAD instead of B-Spline representation (ablation) | BMLiCap · LiDARHuman26M | MPJPE: 70.5 -> 66.8 | Improved |
| use Bezier+TAD instead of linear degradation (ablation) | BMLiCap · LiDARHuman26M | MPJPE: 75.7 -> 66.8 | Improved |
| use Bezier+TAD instead of frequency DCT representation (ablation) | BMLiCap · LiDARHuman26M | MPJPE: 76.4 -> 66.8 | Improved |
| increase levels from 3 to 4 (without TAD) (ablation) | BMLiCap · LiDARHuman26M | MPJPE: 67.9 -> 69.0 | Hurt |
| use stage schedule {32,16,8} instead of {32,8,2} (ablation) | BMLiCap L=3 · LiDARHuman26M | MPJPE: 67.6 -> 66.8 | Improved |
| add block-wise causal mask (ablation) | BMLiCap · LiDARHuman26M | MPJPE: 70.9 -> 66.8 | Improved |
| add multi-level motion aggregator (MMA) (ablation) | BMLiCap · LiDARHuman26M | MPJPE: 68.9 -> 66.8 | Improved |
| add multi-level tokens only (without motion loss, mask, MMA) (ablation) | Base transformer · LiDARHuman26M | MPJPE: 79.0 -> 78.6 | No clear effect |
| replace base representation with Bezier & TAD (ablation) | Base transformer · LiDARHuman26M | MPJPE: 79.0 -> 72.3 | Improved |
| use 32-frame window instead of default window | BMLiCap · NoiseMotion | MPJPE: 34.0 -> 36.9 | Hurt |
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.
- LiveHPS — LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment (CVPR 2024) · better on 3 of 4 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
- OptimalCap: Efficient and Robust LiDAR-Based Motion Capture in Free Environments (TPAMI 2026 · similarity 0.89)
- LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment (CVPR 2024 · similarity 0.87)
- Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimation (AAAI 2025 · similarity 0.85)
- RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method (CVPR 2024 · similarity 0.85)
- ICP-Flow: LiDAR Scene Flow Estimation with ICP (CVPR 2024 · similarity 0.84)
- FreeCap: Hybrid Calibration-Free Motion Capture in Open Environments (AAAI 2025 · 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.
