Author name: Haizhen Xie, Kunpeng Du, Qiangyu Yan, Sen Lu, Jianhong Han, Hanting Chen, Hailin Hu, Jie Hu

arXiv:2505.05209v4 Announce Type: replace
Abstract: 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 ar…