no code implementations • 27 Mar 2023 • Kiran Kumar Ashish Bhyravabhottla, WonSook Lee
Our experiments show that the layer-to-layer training method outperforms the conventional training method for both models.
no code implementations • 14 May 2021 • Qing Ma, Jae Chul Koh, WonSook Lee
In this paper, we introduce frequency domain loss as a constraint to further improve the quality of the RefSR results with fine details and without obvious artifacts.