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 even yields
more visually pleasing results in real video deblurring. Code and pre-trained
models are publicly available at this https URL

本文提出了一种新的视频去模糊框架，Flow-Guided Sparse Transformer（FGST），基于自注意力模块，使用光学流矫正模糊，并采用重复嵌入机制加强长时间依赖关系，结果表明 FGST 在 DVD 和 GOPRO 数据集上明显优于现有方法。