Research map / Point clouds / Shape and surface completion
SynHMR: Synergistic Joint-Mesh Modeling for LiDAR-based Human Mesh Reconstruction
Rui Shi, Xiaoqi An, Lin Zhao, Di Wang, Chen Gong, Le Zhang
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 mesh queries to joint queries in the Geometry-Aware Transformer (ablation) | SynHMR · LiDARHuman26M | MPJPE / PVE: 79.84/102.49 -> 75.89/98.33 | Improved |
| apply full SynHMR (all synergistic components) over single-frame LiDARCap baseline (ablation) | SynHMR · LiDARHuman26M | MPJPE / PVE: 93.74 -> 74.25 MPJPE; 120.14 -> 96.22 PVE (19.49 mm and 23.92 mm reduction) | Improved |
| add Gaussian Fourier Positional Encoding (GFPE) (ablation) | SynHMR · LiDARHuman26M | MPJPE / PVE | Improved |
| add Noise-Augmented Learning (NAL) of perturbed joint queries (ablation) | SynHMR · LiDARHuman26M | MPJPE / PVE | Improved |
| increase sampled vertices from 32 to 512 (ablation) | SynHMR · LiDARHuman26M | MPJPE: 75.21 mm -> 74.21 mm | Improved |
| increase sampled vertices from 32 to 512 (ablation) | SynHMR · LiDARHuman26M | PVE: 97.38 mm -> 96.00 mm | Improved |
| increase sampled vertices from 256 to 512 (ablation) | SynHMR · LiDARHuman26M | MPJPE: 74.25 -> 74.21 | No clear effect |
| increase transformer layers from 3 to 6 (ablation) | SynHMR · LiDARHuman26M | MPJPE: 75.82 -> 74.25 | Improved |
| increase transformer layers from 6 to 7 (ablation) | SynHMR · LiDARHuman26M | MPJPE: 74.25 -> 74.28 | No clear effect |
| replace decoupled coarse-to-fine mesh reconstruction with synergistic joint-mesh modeling | SynHMR vs LiDAR-HMR · SLOPER4D | MPJPE: 47.78 -> 34.09 (reduces MPJPE by 13.69 mm) | Improved |
| synergistic joint-mesh modeling versus LiDAR-HMR | SynHMR vs LiDAR-HMR · Human-M3 | MPJPE: 76.35 -> 56.76 (reduces MPJPE by 19.59 mm) | Improved |
| synergistic joint-mesh modeling versus LiDAR-HMR | SynHMR vs LiDAR-HMR · LiDARHuman26M | MPJPE: 76.07 -> 74.25 (reduces MPJPE by 1.82 mm) | 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.
- LiDARCap — LiDARCap: Long-Range Marker-Less 3D Human Motion Capture With LiDAR Point Clouds (CVPR 2022) · better on 7 of 7 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
- GenHMR: Generative Human Mesh Recovery (AAAI 2025 · similarity 0.87)
- Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimation (AAAI 2025 · similarity 0.86)
- ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization (ICML 2025 · similarity 0.86)
- Self-Supervised 3D Human Mesh Recovery from a Single Image with Uncertainty-Aware Learning (AAAI 2024 · similarity 0.85)
- Synergistic Global-space Camera and Human Reconstruction from Videos (CVPR 2024 · similarity 0.85)
- TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation (CVPR 2024 · 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.
