Search Results for author: Jae Chul Koh

Found 2 papers, 0 papers with code

A Frequency Domain Constraint for Synthetic and Real X-ray Image Super Resolution

no code implementations14 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.

Image Super-Resolution Reference-based Super-Resolution

HRINet: Alternative Supervision Network for High-resolution CT image Interpolation

no code implementations11 Feb 2020 Jiawei Li, Jae Chul Koh, Won-Sook Lee

We combine the idea of ACAI and GANs, and propose a novel idea of alternative supervision method by applying supervised and unsupervised training alternatively to raise the accuracy of human organ structures in CT while keeping high quality.

3D Reconstruction Vocal Bursts Intensity Prediction

Cannot find the paper you are looking for? You can Submit a new open access paper.