CGFormer achieves cross-level interaction by jointly updating the query tokens and decoding masks in every two consecutive layers. In addition, we introduce new splits on datasets for evaluating ...

@inproceedings{lu2021masasr, title={MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution}, author={Liying Lu, Wenbo Li, Xin Tao, Jiangbo Lu, and Jiaya Jia}, ...