This is a research to generate a high-fidelity image using GANs with a small amount of computational resources by reproducing the image from the low-frequency information only using the Wavelet Transform (WT). Specifically, the lost high-frequency information is reconstructed by NN and the inverse Wavelet Transform (iWT) is applied. Although the quality of the generated images decreases a little, they have succeeded in reducing the computational resources from TPUx256 to GPUx4.
TL;DR
This is a research to generate a high-fidelity image using GANs with a small amount of computational resources by reproducing the image from the low-frequency information only using the Wavelet Transform (WT). Specifically, the lost high-frequency information is reconstructed by NN and the inverse Wavelet Transform (iWT) is applied. Although the quality of the generated images decreases a little, they have succeeded in reducing the computational resources from TPUx256 to GPUx4.
Why it matters:
Paper URL
https://arxiv.org/abs/2009.04433
Submission Dates(yyyy/mm/dd)
2020/09/09
Authors and institutions
Seungwook Han, Akash Srivastava, Cole Hurwitz, Prasanna Sattigeri, David D. Cox
Methods
Results
Comments