Research map / Video / Video segmentation and tracking
Flow-Guided Video Inpainting With Scene Templates
Dong Lao, Peihao Zhu, Peter Wonka, Ganesh Sundaramoorthi
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 |
|---|---|---|---|
| replace frame-to-frame propagation with multi-frame scene template aggregation (same optical flow as DFG) (ablation) | flow-guided inpainting · DAVIS | TPSNR: 27.58 -> 30.53 | Improved |
| replace frame-to-frame propagation with multi-frame scene template aggregation (same optical flow as DFG) (ablation) | flow-guided inpainting · DAVIS | TSSIM: 0.852 -> 0.966 | Improved |
| use scene template with FGVC flow initialization | FGVC · DAVIS | TPSNR: 30.71 -> 30.94 | Improved |
| use scene template with FGVC flow initialization | FGVC · Foreground Removal (25 videos) | TPSNR: 32.89 -> 34.56 | Improved |
| use scene template with FGVC flow initialization | FGVC · Foreground Removal (25 videos) | FID: 0.833 -> 0.802 | Improved |
| use FlowNet2 initialization plus SobolevFlow instead of SobolevFlow only (ablation) | Ours+S · Foreground Removal (25 videos) | TPSNR: 30.14 -> 34.58 | Improved |
| use FlowNet2 initialization plus SobolevFlow instead of SobolevFlow only (ablation) | Ours+S · DAVIS | TPSNR: 30.86 -> 29.08 | Hurt |
| add L1 term (temporal median) to the L2 template inpainting (ablation) | scene template inpainting · DAVIS | visual sharpness | Improved |
| combine bilinear interpolation for template with nearest-neighbor for inpainting (ablation) | scene template inpainting · DAVIS | visual quality | Improved |
| apply scene template to fixed-region removal | scene template · DAVIS (fixed regions) | PSNR: 28.02 vs 28.20 | No clear effect |
Closest papers by meaning
- Elevating Flow-Guided Video Inpainting with Reference Generation (AAAI 2025 · similarity 0.90)
- Keyframe-Guided Creative Video Inpainting (CVPR 2025 · similarity 0.87)
- MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing (NeurIPS 2024 · similarity 0.87)
- HomoGen: Enhanced Video Inpainting via Homography Propagation and Diffusion (CVPR 2025 · similarity 0.87)
- Taming generative video models for zero-shot optical flow extraction (NeurIPS 2025 · similarity 0.87)
- FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis (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.
