Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Images

This article proposes crack segmentation augmented by super-resolution (SR) with deep neural networks. In the proposed method, an SR network is jointly trained with a binary segmentation network in an end-to-end manner. This joint learning allows the SR network to be optimized for improving segmentation results. For realistic scenarios, the SR network is extended from nonblind to blind for processing a low-resolution (LR) image degraded by unknown blurs. The joint network is improved by our proposed two extra paths that further encourage the mutual optimization between SR and segmentation. Comparative experiments with state-of-the-art (SoTA) segmentation methods demonstrate the superiority of our joint learning, and various ablation studies prove the effects of our contributions.