AI RESEARCH
LinearSR: Unlocking Linear Attention for Stable and Efficient Image Super-Resolution
arXiv CS.CV
•
ArXi:2510.08771v4 Announce Type: replace Generative models for Image Super-Resolution (SR) are increasingly powerful, yet their reliance on self-attention's quadratic complexity (O(N^2)) creates a major computational bottleneck. Linear Attention offers an O(N) solution, but its promise for photorealistic SR has remained largely untapped, historically hindered by a cascade of interrelated and previously unsolved challenges. This paper