Research map / 3D vision / Human pose estimation
LiveHPS++: Robust and Coherent Motion Capture in Dynamic Free Environment
Yiming Ren, Xiao Han, Yichen Yao, Xiaoxiao Long, Yujing Sun, Yuexin Ma
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-guided body tracker (ablation) | LiveHPS++ · FreeMotion-OBJ | J/V Err (PS): 71.68/90.08 -> 58.11/72.55 | Improved |
| add noise-insensitive velocity predictor and kinematic-aware pose optimizer (ablation) | LiveHPS++ · FreeMotion-OBJ | Jitter: 71.82 -> 30.96 | Improved |
| use trajectory-guided normalization instead of frame-wise normalization (ablation) | LiveHPS++ · FreeMotion-OBJ | Jitter: 43.53 -> 30.96 | Improved |
| use trajectory-guided normalization instead of sequence-wise normalization (ablation) | LiveHPS++ · FreeMotion-OBJ | J/V Err (PS): 85.42/106.91 -> 58.11/72.55 | Improved |
| combine short-term and long-term kinematic optimization (ablation) | KPO · FreeMotion-OBJ | Jitter: 55.50 -> 30.96 (vs short-term) | Improved |
| use LiveHPS++ translation estimation instead of LiveHPS (ablation) | LiveHPS++ · FreeMotion-OBJ | Jitter: 78.09 -> 30.96 | Improved |
| use KPO window size 32 instead of smaller sizes (ablation) | KPO · FreeMotion-OBJ | Jitter | Improved |
| train LiveHPS on NoiseMotion | LiveHPS · FreeMotion-OBJ | J/V Err (PS): 83.33/101.70 -> 70.73/88.43 | Improved |
| train LiveHPS on NoiseMotion | LiveHPS · Sloper4D | J/V Err (PS): 48.28/59.02 -> 53.37/63.15 | Hurt |
| add more NoiseMotion volume to real data (0% to 100%) (ablation) | LiveHPS++ · real data | performance | 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.
- LiveHPS — LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment (CVPR 2024) · better on 4 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
- LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment (CVPR 2024 · similarity 0.91)
- FreeCap: Hybrid Calibration-Free Motion Capture in Open Environments (AAAI 2025 · similarity 0.87)
- RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method (CVPR 2024 · similarity 0.87)
- Neighborhood-Enhanced 3D Human Pose Estimation with Monocular LiDAR in Long-Range Outdoor Scenes (AAAI 2024 · similarity 0.85)
- Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimation (AAAI 2025 · similarity 0.85)
- Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture (CVPR 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.
