Research map / Video / Video segmentation and tracking
Spatio-Temporal Filter Adaptive Network for Video Deblurring
Shangchen Zhou, Jiawei Zhang, Jinshan Pan, Haozhe Xie, Wangmeng Zuo, Jimmy Ren
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 FAC layers for both alignment and deblurring (ablation) | STFAN · Video deblurring dataset (ablation) | PSNR: 29.91 -> 31.24 | Improved |
| add FAC layer for alignment (given deblurring FAC) (ablation) | STFAN · Video deblurring dataset (ablation) | PSNR: 30.59 -> 31.24 | Improved |
| add FAC layer for deblurring (given alignment FAC) (ablation) | STFAN · Video deblurring dataset (ablation) | PSNR: 30.92 -> 31.24 | Improved |
| add alignment branch features (ablation) | STFAN · Video deblurring dataset (ablation) | PSNR: 30.29 -> 31.24 | Improved |
| add deblurring branch features (ablation) | STFAN · Video deblurring dataset (ablation) | PSNR: 30.80 -> 31.24 | Improved |
| add previous restored image to input (B_{t-1}, B_t) -> triplet (ablation) | STFAN · Video deblurring dataset (ablation) | PSNR: 30.87 -> 31.24 | Improved |
| add previous blurry image to input (R_{t-1}, B_t) -> triplet (ablation) | STFAN · Video deblurring dataset (ablation) | PSNR: 30.85 -> 31.24 | Improved |
| add previous blurry image to input, SSIM (ablation) | STFAN · Video deblurring dataset (ablation) | SSIM: 0.930 -> 0.934 | Improved |
| increase adaptive filter size from 3 to 5 (ablation) | STFAN · Video deblurring dataset (ablation) | PSNR: 30.95 -> 31.24 | Improved |
| increase adaptive filter size from 5 to 9 (ablation) | STFAN · Video deblurring dataset (ablation) | PSNR: 31.24 -> 31.30 | No clear effect |
| increase adaptive filter size from 5 to 9 (params) (ablation) | STFAN · Video deblurring dataset (ablation) | Params (M): 5.37 -> 8.14 | Hurt |
| STFAN vs best multi-frame baseline Su | STFAN · Video deblurring dataset (Su et al.) | PSNR: 30.05 -> 31.24 | Improved |
Closest papers by meaning
- Spatio-Temporal Deformable Attention Network for Video Deblurring (ECCV 2022 · similarity 0.90)
- Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring (CVPR 2024 · similarity 0.89)
- Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring (CVPR 2024 · similarity 0.89)
- Learning Scale-Aware Spatio-temporal Implicit Representation for Event-based Motion Deblurring (ICML 2024 · similarity 0.88)
- Parameterized Blur Kernel Prior Learning for Local Motion Deblurring (CVPR 2025 · similarity 0.87)
- FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring (CVPR 2024 · similarity 0.87)
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.
