Research map / 3D vision / 3D generation
DUST: Dual Union of Spatio-Temporal Subspaces for Monocular Multiple Object 3D Reconstruction
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Jointly model spatial and temporal subspaces for 3D reconstruction | DUST · CMU MoCap, two-subject sequences | eX: 0.070 -> 0.058 | Helped |
| Jointly model spatial and temporal subspaces for 3D reconstruction | DUST · CMU MoCap, four-subject sequences | eX: 0.040 -> 0.032 | Helped |
| Handle incomplete 2D tracks through low-rank track completion | DUST · CMU MoCap, two-subject sequences, sparse missing data | eX: 0.058 -> 0.060 | Hurt |
| Handle incomplete 2D tracks through low-rank track completion | DUST · CMU MoCap, two-subject sequences, structured missing data | eX: 0.058 -> 0.070 | Hurt |
| Handle incomplete 2D tracks through low-rank track completion | DUST · CMU MoCap, four-subject sequences, sparse missing data | eX: 0.032 -> 0.033 | Hurt |
| Handle incomplete 2D tracks through low-rank track completion | DUST · CMU MoCap, four-subject sequences, structured missing data | eX: 0.032 -> 0.037 | Hurt |
Closest papers by meaning
- MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion (ICLR 2025 · similarity 0.88)
- Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos (CVPR 2025 · similarity 0.87)
- DUSt3R: Geometric 3D Vision Made Easy (CVPR 2024 · 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)
- Learning Segmentation from Point Trajectories (NeurIPS 2024 · similarity 0.85)
- MUSt3R: Multi-view Network for Stereo 3D Reconstruction (CVPR 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.