AI RESEARCH
GramSR: Visual Feature Conditioning for Diffusion-Based Super-Resolution
arXiv CS.CV
•
ArXi:2604.25457v1 Announce Type: new Despite recent advances, single-image super-resolution (SR) remains challenging, especially in real-world scenarios with complex degradations. Diffusion-based SR methods, particularly those built on Stable Diffusion, leverage strong generative priors but commonly rely on text conditioning derived from semantic captioning.