1 code implementation • 26 Aug 2022 • Sangjun Han, Taeil Hur, Youngmi Hur
LPAE decomposes an image into the approximation image and the detail image in the encoder part and then tries to reconstruct the original image in the decoder part using the two components.
no code implementations • 13 Jan 2018 • Yonggyun Yu, Taeil Hur, Jaeho Jung, In Gwun Jang
Then, as a two-stage refinement, the conditional generative adversarial network (cGAN) is trained with the optimized structures paired at both low and high resolutions, and is connected to the trained CNN-based encoder and decoder network.