AI RESEARCH
Progressive Split Mamba: Effective State Space Modelling for Image Restoration
arXiv CS.CV
•
ArXi:2603.09171v1 Announce Type: new Image restoration requires simultaneously preserving fine-grained local structures and maintaining long-range spatial coherence. While convolutional networks struggle with limited receptive fields, and Transformers incur quadratic complexity for global attention, recent State Space Models (SSMs), such as Mamba, provide an appealing linear-time alternative for long-range dependency modelling. However, naively extending Mamba to 2D images exposes two intrinsic shortcomings.