Abstract
This study proposes a multi-scale fundus image enhancement approach that combines CNN with Mamba, demonstrating clear superiority across multiple benchmarks. The model consistently achieves top performance on public datasets, with the lowest FID and KID scores, and the highest PSNR and SSIM values, particularly excelling at larger image resolutions. Notably, its performance improves as the image size increases, with several metrics reaching optimal values at 1024 × 1024 resolution. Scale generalizability further highlights the model's exceptional structural preservation capability. Additionally, its high VSD and IOU scores in segmentation tasks further validate its practical effectiveness, making it a valuable tool for enhancing fundus images and improving diagnostic accuracy.