Research map / Video / Video segmentation and tracking
Unsupervised Moving Object Segmentation with Atmospheric Turbulence
Dehao Qin, Ripon k Saha, Woojeh Chung, Suren Jayasuriya, Jinwei Ye, Nianyi Li
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 optical flow stabilization by averaging flow over short intervals (ablation) | Ours · DOST | IoU: 0.354 -> 0.703 | Improved |
| add epipolar geometric consistency check (Sampson distance) (ablation) | Ours · DOST | IoU: 0.685 -> 0.703 | Improved |
| add Refine-Net with grouping loss on top of region growing (ablation) | Ours · DOST | J score | Improved |
| increase optical flow interval beyond 4 frames (ablation) | Ours · DOST | accuracy | No clear effect |
| unsupervised turbulence-aware method versus TMO on severe turbulence | Ours · DOST (severe turbulence) | J (Jaccard): 0.235 -> 0.557 | Improved |
| turbulence-free videos: method versus TMO | Ours · synthetic DAVIS 2016 turbulence strength 0 | J score | Hurt |
Closest papers by meaning
- Turb-Seg-Res: A Segment-then-Restore Pipeline for Dynamic Videos with Atmospheric Turbulence (CVPR 2024 · similarity 0.87)
- Unsupervised Space-Time Network for Temporally-Consistent Segmentation of Multiple Motions (CVPR 2023 · similarity 0.87)
- Segmenting the Motion Components of a Video: A Long-Term Unsupervised Model (TPAMI 2025 · similarity 0.87)
- Video Segmentation via Object Flow (CVPR 2016 · similarity 0.86)
- Learning Segmentation from Point Trajectories (NeurIPS 2024 · similarity 0.85)
- GMOS: Grounding Moving Object Segmentation in 3D Space and Time (NeurIPS 2026 · similarity 0.84)
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.
