Research map / Architectures and efficiency / Attention and transformers
FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting
Rui Liu, Hanming Deng, Yangyi Huang, Xiaoyu Shi, Lewei Lu, Wenxiu Sun, Xiaogang Wang, Jifeng Dai, Hongsheng 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 soft split and soft composition (overlapping patches, patch 7) (ablation) | ViB-T · Table 1 ablation | PSNR: 30.50 -> 31.02 | Improved |
| add soft composition only (overlap in composition) (ablation) | ViB-S · Table 1 ablation | PSNR: 30.50 -> 30.74 | Improved |
| add soft split only (ablation) | ViB-S · Table 1 ablation | PSNR: 30.50 -> 30.99 | Improved |
| use both soft split and soft composition rather than soft split only (ablation) | ViB-S · Table 1 ablation | PSNR: 30.99 -> 31.02 | Improved |
| increase ViB-S patch size from 5 to 7 (ablation) | ViB-S · Table 1 ablation | PSNR: 30.91 -> 31.02 | Improved |
| increase ViB-T patch size from 3 to 7 without overlap (ablation) | ViB-T · Table 1 ablation | PSNR: 30.68 -> 30.50 | Hurt |
| replace standard Transformer block with FuseFormer block (F3N sub-token fusion) (ablation) | ViB-S · Table 1 ablation | PSNR: 31.02 -> 31.72 | Improved |
| add normalization in F3N (ablation) | ViF · Table 1 ablation | PSNR: 31.72 -> 31.87 | Improved |
| add normalization in F3N (ablation) | ViF · Table 1 ablation | SSIM: 0.9654 -> 0.9662 | Improved |
| FuseFormer vs STTN on video completion (ablation) | ViF · YouTube-VOS | PSNR: 32.34 -> 33.16 | Improved |
| FuseFormer vs STTN on video completion (ablation) | ViF · DAVIS | PSNR: 30.67 -> 32.54 | Improved |
| replace Transformer block with FuseFormer block, VFID (ablation) | ViB-S · YouTube-VOS | VFID: 0.056 -> 0.051 | Improved |
Closest papers by meaning
- DLFormer: Discrete Latent Transformer for Video Inpainting (CVPR 2022 · similarity 0.88)
- SyFormer: Structure-Guided Synergism Transformer for Large-Portion Image Inpainting (AAAI 2024 · similarity 0.87)
- WaveFormer: Wavelet Transformer for Noise-Robust Video Inpainting (AAAI 2024 · similarity 0.86)
- VSFormer: Visual-Spatial Fusion Transformer for Correspondence Pruning (AAAI 2024 · similarity 0.85)
- vid-TLDR: Training Free Token Merging for Light-weight Video Transformer (CVPR 2024 · similarity 0.85)
- Keyframe-Guided Creative Video Inpainting (CVPR 2025 · similarity 0.85)
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.
