AI RESEARCH
EAM: Enhancing Anything with Diffusion Transformers for Blind Super-Resolution
arXiv CS.CV
•
ArXi:2505.05209v4 Announce Type: replace Utilizing pre-trained Text-to-Image (T2I) diffusion models to guide Blind Super-Resolution (BSR) has become a predominant approach in the field. While T2I models have traditionally relied on U-Net architectures, recent advancements have nstrated that Diffusion Transformers (DiT) achieve significantly higher performance in this domain. In this work, we