AI RESEARCH
Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restoration
arXiv CS.CV
•
ArXi:2602.21917v2 Announce Type: replace Ultra-High-Definition (UHD) image restoration is trapped in a scalability crisis: existing models, bound to pixel-wise operations, demand unsustainable computation. While state space models (SSMs) like Mamba promise linear complexity, their pixel-serial scanning remains a fundamental bottleneck for the millions of pixels in UHD content. We ask: must we process every pixel to understand the image? This paper