Abstract | ||
---|---|---|
Exploiting similar and sharper scene patches in spatio-temporal neighborhoods is critical for video deblurring. However, CNN-based methods show limitations in capturing long-range dependencies and modeling non-local self-similarity. In this paper, we propose a novel framework, Flow-Guided Sparse Transformer (FGST), for video deblurring. In FGST, we customize a self-attention module, Flow-Guided Sparse Window-based Multi-head Self-Attention (FGSW-MSA). For each $query$ element on the blurry reference frame, FGSW-MSA enjoys the guidance of the estimated optical flow to globally sample spatially sparse yet highly related $key$ elements corresponding to the same scene patch in neighboring frames. Besides, we present a Recurrent Embedding (RE) mechanism to transfer information from past frames and strengthen long-range temporal dependencies. Comprehensive experiments demonstrate that our proposed FGST outperforms state-of-the-art (SOTA) methods on both DVD and GOPRO datasets and yields visually pleasant results in real video deblurring. https://github.com/linjing7/VR-Baseline |
Year | Venue | DocType |
---|---|---|
2022 | International Conference on Machine Learning | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
10 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jing Lin | 1 | 0 | 1.69 |
Yuanhao Cai | 2 | 4 | 3.43 |
Xiaowan Hu | 3 | 4 | 3.09 |
Wang H | 4 | 71 | 29.35 |
Youliang Yan | 5 | 0 | 1.35 |
Xueyi Zou | 6 | 6 | 2.49 |
Henghui Ding | 7 | 36 | 10.78 |
Zhang Yulun | 8 | 206 | 22.15 |
Radu Timofte | 9 | 1880 | 118.45 |
Luc Van Gool | 10 | 27566 | 1819.51 |