5-Degradation Blind All-in-One Image Restoration

Blind All-in-One Image Restoration aims to remove various degradations from an input image without prior knowledge of the degradation type or severity. In this task, we include 5 of the most common image restoration tasks with five degradations: rain, haze, noise, blur, and low-light conditions. This task focuses on five common image restoration tasks, each addressing a specific degradation: rain , haze, noise, blur, and low-light conditions. For training, we utilize the following datasets: Rain200L for deraining, RESIDE for dehazing, WED and BSD400 for denoising with a noise level of σ=25, GoPro for deblurring, and LoLv1 for low-light enhancement. For evaluation, we employ: Rain100L for deraining, SOTS (outdoor) for dehazing, BSD68 for denoising with σ=25, GoPro for deblurring, and LoLv1 for low-light enhancement. The performance of the models is assessed by reporting the average PSNR across all five evaluation datasets, reflecting the overall capability of the model to handle diverse degradations.