A degradation-aware enhancement network with fused features for fundus images

Lots of fundus images are not gradable for clinical diagnosis and computer-aided diagnosis of ocular diseases due to poor quality. In order to restore fundus images from different kinds of degradation, a degradation-aware fundus enhancement model with fused features under different receptive fields is proposed in this paper. We obtain fused features from multiple receptive fields by combining a global path with spectral convolution and a local path with degradation attention. Degradation features and degradation labels are calculated on each image and they are applied for a flexible adaption to different degradations. Experiments on both synthetic and real image datasets demonstrate that our method corrects low-quality images effectively and has generalization ability for clinical datasets from different sources.