Research map / 3D vision / 3D generation
Robust Spatio-Temporal Clustering and Reconstruction of Multiple Deformable Bodies
Antonio Agudo, Francesc Moreno-Noguer
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 |
|---|---|---|---|
| estimate camera rotation jointly (DUST2-TS) instead of fixing it (DUST-TS) | DUST-TS · CMU two subjects, clean data | eX: 0.092 -> 0.089 | Improved |
| estimate camera rotation jointly (DUST2-TS) instead of fixing it (DUST-TS) | DUST-TS · CMU four subjects, clean data | eX: 0.085 -> 0.079 | Improved |
| add 70% sparse missing data (ablation) | DUST-TS · CMU two subjects | eX: 0.092 -> 0.093 | Hurt |
| add 20% structured missing tracks (ablation) | DUST-TS · CMU two subjects | eX: 0.092 -> 0.103 | Hurt |
| add Gaussian noise to observations (ablation) | DUST-TS · CMU two subjects | eX: 0.092 -> 0.107 | Hurt |
| add 70% sparse missing data (ablation) | DUST2-TS · CMU two subjects | eX: 0.089 -> 0.110 | Hurt |
| add noise to observations (ablation) | DUST2-TS · CMU four subjects | eX: 0.079 -> 0.096 | Hurt |
| add 40% random missing data (ablation) | DUST-TS · CMU four subjects, known rotation | eX: 0.027 -> 0.031 | Hurt |
| add 40% random missing data (ablation) | DUST-TS · CMU two subjects, known rotation | eX: 0.049 -> 0.053 | Hurt |
| use DUST-TS spatio-temporal union of subspaces instead of DUST | DUST · CMU two subjects, known rotation | eX: 0.058 -> 0.049 | Improved |
| use DUST-TS instead of DUST | DUST · UMPM p2_meet_1 | eX: 0.224 -> 0.208 | Improved |
| use DUST2-TS instead of DUST-TS when artifacts are heavy | DUST-TS · CMU two subjects with artifacts | eX: 0.093 -> 0.110 | Hurt |
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.
- DUST — DUST: Dual Union of Spatio-Temporal Subspaces for Monocular Multiple Object 3D Reconstruction (CVPR 2017) · better on 4 of 4 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
- DUST: Dual Union of Spatio-Temporal Subspaces for Monocular Multiple Object 3D Reconstruction (CVPR 2017 · similarity 0.93)
- Image Collection Pop-Up: 3D Reconstruction and Clustering of Rigid and Non-Rigid Categories (CVPR 2018 · similarity 0.90)
- Unsupervised 3D Reconstruction and Grouping of Rigid and Non-Rigid Categories (TPAMI 2020 · similarity 0.88)
- Learning Category-Specific Deformable 3D Models for Object Reconstruction (TPAMI 2016 · similarity 0.88)
- Shape of Motion: 4D Reconstruction from a Single Video (ICCV 2025 · similarity 0.88)
- Learning Segmentation from Point Trajectories (NeurIPS 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.
