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

arXiv:2302.12491v3 Announce Type: replace
Abstract: 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 …

abstract arxiv binary blind cs.ai cs.cv eess.iv images network networks neural networks paper segmentation super resolution type