Research map / Point clouds / Point cloud classification
Motion Keyframe Interpolation for Any Human Skeleton using Point Cloud-based Human Motion Data Homogenisation
Clinton A Mo, Kun Hu, Chengjiang Long, Dong Yuan, Zhiyong Wang
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 Rest Pose Augmentation (RPA) to PC-MRL training (ablation) | PC-MRL · CMU Golf, interval 30 | L2P: 0.3622 -> 0.2706 | Improved |
| add RPA to PC-MRL training (ablation) | PC-MRL · CMU Walking & Running, interval 30 | L2P: 0.3417 -> 0.2848 | Improved |
| add RPA to PC-MRL training (ablation) | PC-MRL · CMU Basketball, interval 5 | L2P: 0.0767 -> 0.0752 | No clear effect |
| supervise interpolation with PC-MRL point-cloud-adapted data instead of native CMU data | CITL · CMU Swimming, interval 30 | L2P: 0.7475 -> 0.7139 | Improved |
| supervise interpolation with PC-MRL instead of native CMU data | CITL · CMU Basketball, interval 30 | L2P: 0.5708 -> 0.6662 | Hurt |
| supervise CITL with PC-MRL data instead of primal-skeleton retargeted data | CITL · CMU interpolation, interval 30 | L2P: 1.1524 -> 0.4960 | Improved |
| use PC-MRL point cloud retargeting instead of primal skeleton for unpaired retargeting | motion retargeting LaFAN1 to CMU · LaFAN1 to CMU re-targeting | end-effector loss (x100): 9.6990 -> 5.6258 | Improved |
| learned interpolation vs LERP with PC-MRL supervision | PC-MRL · CMU Walking & Running, interval 30 | L2P: 0.5527 -> 0.2848 | Improved |
Closest papers by meaning
- PUMPS: Skeleton-Agnostic Point-based Universal Motion Pre-Training for Synthesis in Human Motion Tasks (ICCV 2025 · similarity 0.90)
- Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation (CVPR 2026 · similarity 0.88)
- SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology (NeurIPS 2026 · similarity 0.87)
- Learning Implicit Representation for Reconstructing Articulated Objects (ICLR 2024 · similarity 0.86)
- SPEAL: Skeletal Prior Embedded Attention Learning for Cross-Source Point Cloud Registration (AAAI 2024 · similarity 0.86)
- Controllable Human-centric Keyframe Interpolation with Generative Prior (NeurIPS 2025 · similarity 0.86)
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.
