Research map / Detection and segmentation / 3D detection and driving
Motion From Structure (MfS): Searching for 3D Objects in Cluttered Point Trajectories
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 |
|---|---|---|---|
| Add support-track selection before matching (ablation) | MfS · Synthetic data | IoU | Helped |
| Add support-track selection before matching (ablation) | MfS · Synthetic data | Precision | Helped |
| Add support-track selection before matching (ablation) | MfS · Synthetic data | Recall | Helped |
| Add guided sampling of support tracks instead of uniform sampling (ablation) | MfS with support-track selection · Synthetic data | IoU | Helped |
| Add guided sampling of support tracks instead of uniform sampling (ablation) | MfS with support-track selection · Synthetic data | Precision | Helped |
| Add guided sampling of support tracks instead of uniform sampling (ablation) | MfS with support-track selection · Synthetic data | Recall | Helped |
| Remove corner tracks from the observed object | STGS-R · Synthetic data with missing corner tracks | IoU | Hurt |
| Remove corner tracks from the observed object | STGS-R · Synthetic data with missing corner tracks | Precision | Hurt |
| Remove corner tracks from the observed object | STGS-R · Synthetic data with missing corner tracks | Recall | Hurt |
| Use tracks alone when background trajectories form a shape similar to the target model | MfS · Real video with panning camera | Alignment correctness | Hurt |
Closest papers by meaning
- VGGSfM: Visual Geometry Grounded Deep Structure From Motion (CVPR 2024 · similarity 0.87)
- Learning Segmentation from Point Trajectories (NeurIPS 2024 · similarity 0.86)
- Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping (NeurIPS 2025 · similarity 0.86)
- M3SOT: Multi-Frame, Multi-Field, Multi-Space 3D Single Object Tracking (AAAI 2024 · similarity 0.86)
- M^3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation (CVPR 2025 · similarity 0.85)
- GMOS: Grounding Moving Object Segmentation in 3D Space and Time (NeurIPS 2026 · 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.