Research map / Video / Video segmentation and tracking
CIRI: Curricular Inactivation for Residue-aware One-shot Video Inpainting
Weiying Zheng, Cheng Xu, Xuemiao Xu, Wenxi Liu, Shengfeng He
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 hard masking with feature-level target inactivation (ablation) | E2FGVI · Synthetic one-shot (local) | PSNR: 28.11 -> 28.77 | Improved |
| add dual-curriculum learning (ablation) | E2FGVI + target inactivation · Synthetic one-shot (local) | VFID: 0.755 -> 0.730 | Improved |
| add contextual loss in online residue removal (ablation) | CIRI · Synthetic one-shot (local) | PSNR: 28.89 -> 28.96 | Improved |
| add residue loss in online residue removal (ablation) | CIRI · Synthetic one-shot (local) | PSNR: 28.96 -> 29.01 | Improved |
| add contextual and residue losses at test time (ablation) | CIRI · Synthetic one-shot | J&F of predicted masks: 94.84 -> 95.32 | Improved |
| add online residue removal (ablation) | CIRI · Inference time | seconds: 9.22 -> 40.67 | Hurt |
| plug CIRI into existing inpainting backbones | DSTT · Synthetic one-shot (local) | PSNR: 26.34 -> 27.48 | Improved |
| plug CIRI into E2FGVI | E2FGVI · Synthetic one-shot (global) | PSNR: 36.45 -> 36.84 | Improved |
| use IIVI mask propagation instead of STCN predicted masks | IIVI · Synthetic one-shot (local) | PSNR: 27.82 -> 19.26 | Hurt |
Closest papers by meaning
- CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility (AAAI 2025 · similarity 0.86)
- AVID: Any-Length Video Inpainting with Diffusion Model (CVPR 2024 · similarity 0.85)
- Keyframe-Guided Creative Video Inpainting (CVPR 2025 · similarity 0.85)
- Video Diffusion Models Are Strong Video Inpainter (AAAI 2025 · similarity 0.84)
- Infinite-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation (AAAI 2025 · similarity 0.84)
- Elevating Flow-Guided Video Inpainting with Reference Generation (AAAI 2025 · 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.
