Research map / 3D vision / Depth and stereo
MonoMobility: Zero-Shot 3D Mobility Analysis from Monocular Videos
Hongyi Zhou, Yulan Guo, Xiaogang Wang, Kai Xu
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 motion axis initialization from point cloud registration (ablation) | MonoMobility · Motion axis initialization ablation (own dataset) | Type accuracy: 0.667 -> 1.0 | Improved |
| add motion axis initialization from point cloud registration (ablation) | MonoMobility · Motion axis initialization ablation (own dataset) | AE (deg): 10.235 -> 1.143 | Improved |
| add motion axis initialization from point cloud registration (ablation) | MonoMobility · Motion axis initialization ablation (own dataset) | PE (cm): 8.978 -> 4.843 | Improved |
| add motion axis initialization from point cloud registration (ablation) | MonoMobility · Motion axis initialization ablation (own dataset) | IOU: 0.956 -> 0.956 | No clear effect |
| add rendering loss (ablation) | MonoMobility · Loss ablation (own dataset) | AE (deg): 7.264 -> 1.143 | Improved |
| add rendering loss (ablation) | MonoMobility · Loss ablation (own dataset) | PE (cm): 10.474 -> 4.843 | Improved |
| add normal loss (ablation) | MonoMobility · Loss ablation (own dataset) | AE (deg): 4.427 -> 1.143 | Improved |
| add normal loss (ablation) | MonoMobility · Loss ablation (own dataset) | PE (cm): 6.058 -> 4.843 | Improved |
| add motion loss (ablation) | MonoMobility · Loss ablation (own dataset) | Type accuracy: 0.889 -> 1.0 | Improved |
| add motion loss (ablation) | MonoMobility · Loss ablation (own dataset) | AE (deg): 4.995 -> 1.143 | Improved |
| add motion loss (ablation) | MonoMobility · Loss ablation (own dataset) | PE (cm): 7.772 -> 4.843 | Improved |
| add dynamic scene optimization after initialization (ablation) | MonoMobility · Articulated motion axis (own dataset, mean) | AE (deg): 12.054 -> 1.262 | Improved |
Closest papers by meaning
- Articulation in Motion: Prior-free Part Mobility Analysis for Articulated Objects By Dynamic-Static Disentanglement (ICLR 2026 · similarity 0.90)
- Shape of Motion: 4D Reconstruction from a Single Video (ICCV 2025 · similarity 0.89)
- World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.87)
- Seurat: From Moving Points to Depth (CVPR 2025 · similarity 0.87)
- Articulation in Prime: Primitive-Based Articulated Object Understanding from a Single Casual Video (NeurIPS 2026 · similarity 0.86)
- S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video (ICML 2024 · 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.
