Multi-patch multi-scale model for motion deblurring with high-frequency information

Nowadays deep learning-based models have made encouraging accomplishments in the field of image motion deblurring, but this type of algorithms does not effectively use the known prior knowledge and the physical model of motion blur. So as to settle the above disputes, this paper suggests a multi-patch multi-scale input model that fuses high-frequency information, structural self-similarity (SSS), multi-scale channel spatial attention (MSCSA), and superpixel gradient loss for motion deblurring. The multi-patch multi-scale input model can fully extract the salient information, scale information, and high-frequency information of the image to restore the sharp image. The SSS module can take full advantage of the prior information of the structure self-similarity of the image. And the MSCSA module dynamically and selectively enhances relevant features and suppresses irrelevant features by fusing spatial, scale, and channel characteristics. Moreover, this paper advises a superpixel gradient loss function, which can remove motion blur and restore sharp images more effectively. And to increase the diversity of scenes, for the first time, we propose a motion blur dataset (Underwater-Blur) specifically for underwater scenes. Massive comparative experiments conducted on three public datasets of GoPro, RealBlur, RWBI, and the Underwater-Blur dataset prove that our model outperforms the state-of-the-art in terms of comprehensive performance.