Research map / Video / Video segmentation and tracking
Proposal-based Video Completion
Yuan-Ting Hu, Heng Wang, Nicolas Ballas, Kristen Grauman, Alexander G. Schwing
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 proposal generation with single-convolution fusion (ablation) | 3D inpainting net · YouTube VOS val | LPIPS: 0.415 -> 0.377 | Improved |
| add proposal generation with single-convolution fusion (ablation) | 3D inpainting net · YouTube VOS val | PSNR: 14.33 -> 14.41 | Improved |
| add proposal generation with single-convolution fusion (ablation) | 3D inpainting net · YouTube VOS test | PSNR: 11.80 -> 11.84 | Improved |
| add the proposal-fusion classifier (ablation) | 3D net + proposals · YouTube VOS val | PSNR: 14.41 -> 16.22 | Improved |
| add the proposal-fusion classifier (ablation) | 3D net + proposals · YouTube VOS test | PSNR: 11.84 -> 13.29 | Improved |
| add the proposal-fusion classifier (ablation) | 3D net + proposals · YouTube VOS val | LPIPS: 0.377 -> 0.301 | Improved |
| add the proposal-fusion classifier (ablation) | 3D net + proposals · YouTube VOS test | LPIPS: 0.433 -> 0.388 | Improved |
| use proposals instead of optical-flow propagation (FGI) | FGI · YouTube VOS test | PSNR (inpainted region): 10.890 -> 13.292 | Improved |
| use proposals instead of optical-flow propagation (FGI) | FGI · DAVIS | LPIPS (inpainted region): 0.353 -> 0.381 | Hurt |
| use proposals instead of optical-flow propagation (FGI) | FGI · DAVIS | PSNR (inpainted region): 10.974 -> 12.453 | Improved |
| use proposals instead of optical-flow propagation (FGI) | FGI · DAVIS | runtime per frame: 37.63 s -> 0.69 s | Improved |
| use proposal-based method instead of Onion-Peel network (OPN) | OPN · YouTube VOS test | PSNR (inpainted region): 12.242 -> 13.292 | Improved |
Closest papers by meaning
- Deep Flow-Guided Video Inpainting (CVPR 2019 · similarity 0.92)
- Towards an End-to-End Framework for Flow-Guided Video Inpainting (CVPR 2022 · similarity 0.91)
- Video Diffusion Models Are Strong Video Inpainter (AAAI 2025 · similarity 0.87)
- Elevating Flow-Guided Video Inpainting with Reference Generation (AAAI 2025 · similarity 0.87)
- Keyframe-Guided Creative Video Inpainting (CVPR 2025 · similarity 0.87)
- AVID: Any-Length Video Inpainting with Diffusion Model (CVPR 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.
