Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Images
This work addresses crack detection in degraded images for applications like infrastructure inspection, but it is incremental as it builds on existing joint learning approaches with specific enhancements.
The paper tackles the problem of crack segmentation in low-resolution images by jointly training a super-resolution network with a segmentation network, enabling the SR network to optimize for segmentation performance. The method achieves superior results compared to state-of-the-art segmentation techniques, as demonstrated in comparative experiments.
This paper proposes crack segmentation augmented by super resolution (SR) with deep neural networks. In the proposed method, a 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 non-blind to blind for processing a low-resolution 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.