Multiple Generative Adversarial Networks Analysis for Predicting Photographers' Retouching
This addresses the problem of enabling non-experts to achieve professional-quality photo retouching, but it appears incremental as it builds on existing GAN methods.
The study tackled the problem of automating professional photo retouching by using deep learning, specifically generative adversarial networks (GANs), to mimic artists' work, and found that certain models provided the best results, though no concrete numbers were specified.
Anyone can take a photo, but not everybody has the ability to retouch their pictures and obtain result close to professional. Since it is not possible to ask experts to retouch thousands of pictures, we thought about teaching a piece of software how to reproduce the work of those said experts. This study aims to explore the possibility to use deep learning methods and more specifically, generative adversarial networks (GANs), to mimic artists' retouching and find which one of the studied models provides the best results.