CU-Mamba: Selective State Space Models with Channel Learning for Image Restoration

arXiv:2404.11778v1 Announce Type: new
Abstract: Reconstructing degraded images is a critical task in image processing. Although CNN and Transformer-based models are prevalent in this field, they exhibit inherent limitations, such as inadequate long-range dependency modeling and high computational costs. To overcome these issues, we introduce the Channel-Aware U-Shaped Mamba (CU-Mamba) model, which incorporates a dual State Space Model (SSM) framework into the U-Net architecture. CU-Mamba employs a Spatial SSM module for global context encoding and a Channel SSM component to …

abstract arxiv cnn computational costs cs.cv image image processing image restoration images limitations mamba modeling processing restoration space state state space models transformer transformer-based models type