Research map / Video / Video segmentation and tracking
Gated Spatio-Temporal Attention-Guided Video Deblurring
Check 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 |
|---|---|---|---|
| use gated spatio-temporal attention instead of ungated spatio-temporal attention (ablation) | Video deblurring network · GOPRO | PSNR: 31.40 -> 31.61 | Helped |
| add spatio-temporal attention to the encoder-decoder backbone (ablation) | Video deblurring network · GOPRO | PSNR: 30.70 -> 31.40 | Helped |
| add reinforcement-learning frame selection to gated spatio-temporal attention (ablation) | Net3 · GOPRO | PSNR: 31.61 -> 32.10 | Helped |
| replace the proposed attention block with the non-local attention block from [33] (ablation) | Video deblurring network · GOPRO | PSNR: 31.61 -> 31.17 | Hurt |
| use FSN to select up to 5 neighboring frames instead of a fixed ±2 neighborhood (ablation) | Video deblurring network · GOPRO | PSNR: 31.61 -> 32.10 | Helped |
| select 5 frames randomly instead of selecting them with FSN (ablation) | Video deblurring network · GOPRO | PSNR: 31.65 -> 32.10 | Hurt |
| increase the FSN maximum from 3 to 5 neighboring frames (ablation) | Video deblurring network · GOPRO | PSNR: 31.87 -> 32.10 | Helped |
| increase the FSN maximum from 5 to 7 neighboring frames (ablation) | Video deblurring network · GOPRO | PSNR: 32.10 -> 32.19 | Helped |
| use the proposed deblurring method instead of TSP | Video deblurring · DVD | PSNR: 32.13 -> 32.53 | Helped |
| use the proposed deblurring method instead of TSP | Video deblurring · GOPRO | PSNR: 31.67 -> 32.10 | Helped |
Closest papers by meaning
- Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring (CVPR 2024 · similarity 0.89)
- Motion Deblurring via Spatial-Temporal Collaboration of Frames and Events (AAAI 2024 · similarity 0.88)
- Motion-adaptive Transformer for Event-based Image Deblurring (AAAI 2025 · similarity 0.88)
- Learning Scale-Aware Spatio-temporal Implicit Representation for Event-based Motion Deblurring (ICML 2024 · similarity 0.87)
- Frequency-aware Event-based Video Deblurring for Real-World Motion Blur (CVPR 2024 · similarity 0.86)
- Parameterized Blur Kernel Prior Learning for Local Motion Deblurring (CVPR 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.