Research map / Video / Video segmentation and tracking
Video Inpainting by Jointly Learning Temporal Structure and Spatial Details
Read the paperCheck 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 |
|---|---|---|---|
| Combine 3D temporal guidance with 2D detail recovery | Video inpainting · FaceForensics | L1 loss: 6.77 -> 6.27 | Helped |
| Combine 3D temporal guidance with 2D detail recovery | Video inpainting · Caltech | L1 loss: 11.16 -> 9.56 | Helped |
| Use down-sample rate r=4 instead of the standard resolution (ablation) | CombCN · 300VW | L1 loss: 4.20 -> 6.39 | Hurt |
| Down-sample in the time axis (ablation) | CombCN · 300VW | L1 loss: 4.20 -> 8.13 | Hurt |
| Disable 3DCN fine-tuning while training CombCN (ablation) | CombCN · 300VW | L1 loss: 4.20 -> 5.18 | Hurt |
| Train both networks jointly from scratch instead of pre-training 3DCN (ablation) | CombCN · 300VW | L1 loss: 4.20 -> 6.31 | Hurt |
Closest papers by meaning
- Deep Video Inpainting (CVPR 2019 · similarity 0.92)
- Progressive Temporal Feature Alignment Network for Video Inpainting (CVPR 2021 · similarity 0.90)
- Building an End-to-End Spatial-Temporal Convolutional Network for Video Super-Resolution (AAAI 2017 · similarity 0.88)
- Semi-Supervised Video Inpainting With Cycle Consistency Constraints (CVPR 2023 · similarity 0.88)
- Image Inpainting via Generative Multi-column Convolutional Neural Networks (NeurIPS 2018 · similarity 0.88)
- Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos (NeurIPS 2025 · 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.