Beyond the Ground Truth: Enhanced Supervision for Image Restoration

ArXi:2512.03932v3 Announce Type: replace Deep learning-based image restoration has achieved significant success. However, when addressing real-world degradations, model performance is limited by the quality of groundtruth images in datasets due to practical constraints in data acquisition. To address this limitation, we propose a novel framework that enhances existing ground truth images to provide higher-quality supervision for real-world restoration.