Research map / 3D vision / Depth and stereo
4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface
Yang Li, Hikari Takehara, Takafumi Taketomi, Bo Zheng, Matthias Nießner
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 |
|---|---|---|---|
| train on DeformingThings4D instead of FlyingThings3D | FlowNet3D · DeformingThings4D (scene flow) | EPE (cm): 7.36 -> 3.74 | Improved |
| train on DeformingThings4D instead of FlyingThings3D | FlowNet3D · DeepDeform (scene flow) | EPE (cm): 21.07 -> 13.08 | Improved |
| train on DeformingThings4D instead of FlyingThings3D | FlowNet3D · DeepDeform (scene flow) | ACC(10): 45.09% -> 61.26% | Improved |
| train on DeformingThings4D instead of FlyingThings3D | FlowNet3D · KITTI SFlow (scene flow) | EPE (cm): 16.88 -> 17.01 | No clear effect |
| train on DeformingThings4D instead of FlyingThings3D | FlowNet3D · KITTI SFlow (scene flow) | ACC(10): 67.17% -> 71.67% | Mixed |
| replace ARAP deformation with learned Motion Complete | ARAP Deformation · Unobserved-surface motion (average over 6 sequences) | EPE (cm): 31.72 -> 24.08 | Improved |
| replace ARAP deformation with learned Motion Complete | ARAP Deformation · Dairy Cow (Attack) | EPE (cm): 2.73 -> 2.90 | Hurt |
| replace ARAP deformation with learned Motion Complete | ARAP Deformation · Moose Bull (Walk) | EPE (cm): 1.27 -> 1.34 | Hurt |
| add post-processing (PP) to Motion Complete (ablation) | Motion Complete · Unobserved-surface motion (average over 6 sequences) | EPE (cm): 24.08 -> 18.69 | Improved |
| replace rigid fitting with ARAP deformation | Rigid Fitting · Unobserved-surface motion (average over 6 sequences) | EPE (cm): 94.23 -> 31.72 | Improved |
| add post-processing to Motion Complete on Deer Stag (ablation) | Motion Complete · Deer Stag (Attack) | EPE (cm): 4.08 -> 2.05 | Improved |
Closest papers by meaning
- 4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians (CVPR 2025 · similarity 0.90)
- Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking (CVPR 2024 · similarity 0.90)
- Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video (NeurIPS 2025 · similarity 0.89)
- Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding (NeurIPS 2025 · similarity 0.89)
- Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos (CVPR 2025 · similarity 0.88)
- 4DP-QA: Scalable QA for 4D Perception in Vision Language Models (CVPR 2026 · similarity 0.87)
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.
