Research map / 3D vision / Human pose estimation
Within the Dynamic Context: Inertia-aware 3D Human Modeling with Pose Sequence
Yutong Chen, Yifan Zhan, Zhihang Zhong, Wei Wang, Xiao Sun, Yu Qiao, Yinqiang Zheng
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 current pose condition alongside delta pose sequence (ablation) | Dyco · I3D-Human novel view | PSNR: 30.89 -> 31.22 | Improved |
| add delta pose sequence condition to pose-only model (ablation) | Dyco · I3D-Human novel view | PSNR: 30.40 -> 31.22 | Improved |
| add delta pose sequence on top of nothing (no pose, no delta) (ablation) | Dyco · I3D-Human novel view | DME: 5.21 -> 4.52 | Improved |
| add localized kinematic spatial dependency (ablation) | Dyco · I3D-Human novel pose | PSNR: 29.58 -> 30.12 | Improved |
| add localized spatial dependency (ablation) | Dyco · I3D-Human novel view | DME: 4.42 -> 4.52 | No clear effect |
| feed delta pose into canonical volume as well as non-rigid transform (ablation) | Dyco · I3D-Human novel view | DME: 5.14 -> 4.52 | Improved |
| use delta pose sequence instead of absolute pose sequence (ablation) | Dyco · I3D-Human novel view | PSNR: 29.93 -> 31.22 | Improved |
| use axis-angle instead of quaternion delta pose representation (ablation) | Dyco · I3D-Human novel view | LPIPS x1000: 36.00 -> 34.54 | Improved |
| lengthen delta sequence from 6 to 12 frames (ablation) | Dyco · I3D-Human novel pose | PSNR: 30.12 -> 29.69 | Hurt |
| shorten delta sequence from 6 to 2 frames (ablation) | Dyco · I3D-Human novel pose | PSNR: 30.12 -> 29.89 | Hurt |
| reduce step s and s_d from 25 to 12 (ablation) | Dyco · I3D-Human novel view | PSNR: 31.22 -> 30.99 | Hurt |
| use Dyco instead of 3DGS-Avatar on tightly clothed ZJU-MoCap novel pose | Dyco · ZJU-MoCap novel pose | PSNR: 30.01 vs 29.71 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- 3DGS-Avatar — 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024) · better on 5 of 6 shared results
- NeuralBody — Neural Body: Implicit Neural Representations With Structured Latent Codes for Novel View Synthesis of Dynamic Humans (CVPR 2021) · better on 1 of 2 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
- Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial Sensors (CVPR 2024 · similarity 0.88)
- SurMo: Surface-based 4D Motion Modeling for Dynamic Human Rendering (CVPR 2024 · similarity 0.86)
- Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose Interaction (CVPR 2025 · similarity 0.85)
- DLCA-Recon: Dynamic Loose Clothing Avatar Reconstruction from Monocular Videos (AAAI 2024 · similarity 0.85)
- HiPoser: 3D Human Pose Estimation with Hierarchical Shared Learning at Parts-Level Using Inertial Measurement Units (AAAI 2025 · similarity 0.85)
- BEDLAM2.0: Synthetic humans and cameras in motion (NeurIPS 2025 · 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.
