Recovering rain images using Self-supervised Reinforcement Learning for image deraining.
Restormer-Plus effectively addresses the challenges of real-world single image deraining by combining a modified Restormer model with median filtering, weighted averaging, and post-processing techniques, achieving state-of-the-art results in the GT-RAIN Challenge.
This research paper introduces DFSSM, a novel deep learning model for single image deraining that leverages the strengths of state space models (SSMs) and frequency domain processing to achieve state-of-the-art performance in removing rain streaks and restoring image quality.