Research map / Video / Video segmentation and tracking
Real-World Video Deblurring: A Benchmark Dataset and an Efficient Recurrent Neural Network
Zhihang Zhong, Ye Gao, Yinqiang Zheng, Bo Rui Zheng, Imari Sato
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 high-level feature fusion across frames (ablation) | ESTRNN (matched cost) · GOPRO (ablation, matched cost) | PSNR (dB): 30.29 -> 30.46 | Improved |
| add RDB cell instead of residual block (ablation) | ESTRNN (matched cost) · GOPRO (ablation, matched cost) | PSNR (dB): 30.29 -> 30.51 | Improved |
| add GSA module instead of channel concatenation (ablation) | ESTRNN (matched cost) · GOPRO (ablation, matched cost) | PSNR (dB): 30.55 -> 30.79 | Improved |
| add fusion and RDB cell together (ablation) | ESTRNN (matched cost) · GOPRO (ablation, matched cost) | PSNR (dB): 30.29 -> 30.55 | Improved |
| increase RDB blocks from 3 to 15 (ablation) | ESTRNN · GOPRO (RDB blocks / neighboring frames) | PSNR (dB): 29.74 -> 31.27 | Improved |
| increase RDB blocks (B15C80) instead of channels (B9C90) at equal cost (ablation) | ESTRNN · GOPRO | PSNR (dB): 31.07 -> 31.27 | Improved |
| use future frames too (F3P3 vs F0P1) (ablation) | ESTRNN GSA · GOPRO (RDB blocks / neighboring frames) | PSNR (dB): 30.54 -> 30.82 | Improved |
| no future frames, only past frames (F0P3) (ablation) | ESTRNN GSA · GOPRO (RDB blocks / neighboring frames) | PSNR (dB): 30.69 vs 30.79 (F2P2) | No clear effect |
| increase channels C from 60 to 90 (ablation) | ESTRNN · GOPRO | PSNR (dB): 30.12 -> 31.07 | Improved |
| train on real-world BSD instead of synthetic GOPRO, test on cross dataset | ESTRNN (B15C80) · Cross-validation BSD vs GOPRO | PSNR (dB): 26.46 on GOPRO vs 19.48 on BSD | Improved |
| longer exposure (3ms-24ms vs 1ms-8ms) | ESTRNN (B15C80) · BSD | PSNR (dB): 33.36 -> 31.39 | Hurt |
| higher-frame-rate synthetic data (2000fps) | Synthetic training data · BSD cross-validation | qualitative | No clear effect |
Closest papers by meaning
- Efficient Spatio-Temporal Recurrent Neural Network for Video Deblurring (ECCV 2020 · similarity 0.96)
- Deep Recurrent Neural Network with Multi-Scale Bi-directional Propagation for Video Deblurring (AAAI 2022 · similarity 0.91)
- Online Video Deblurring via Dynamic Temporal Blending Network (ICCV 2017 · similarity 0.91)
- Cascaded Deep Video Deblurring Using Temporal Sharpness Prior and Non-Local Spatial-Temporal Similarity (TPAMI 2023 · similarity 0.90)
- Recurrent Neural Networks With Intra-Frame Iterations for Video Deblurring (CVPR 2019 · similarity 0.90)
- Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring (CVPR 2024 · similarity 0.89)
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.
