“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

In many existing solutions of image-to-image rendering problems, the only focus is to find the closest output of the Generative Adversarial Network (GAN). In this research article, authors propose a generative adversarial network, a solution to pixel-to-pixel rendering problems and reduced the loss function to the maximum under all interactions. For achieving the best result, we have considered the mean square loss function in the generator and binary cross for the discriminator. Our proposed model deals with not only images but also read sketches where the edges are not sharp too. We have used a facade dataset to test our proposed model.

http://it-in-industry.org/index.php/itii/article/download/458/402

Aleem Ali

Papers

Conditional gans as a solution to image-to-image rendering problems