An implementation of "Naturalness-Preserving Image Tone Enhancement Using Generative Adversarial Networks", Pacific Graphics 2019 Best Paper
This project uses GAN (Generative Adversarial Netowrk) for naturalness-preserving image tone enhancement with an automatically generated paired dataset. The paired dataset consists of input images from Five-K dataset[1] and the results of a previous classical filtering method[2] that produces drastic but possibly unnatural-looking tone enhancement results.
For more details regarding this technique, please refer to the paper
For testing our network, please download the pretrained model and move the model to the "checkpoint" folder.
Hyeongseok Son (sonhs@postech.ac.kr)
Cite our papers if you find this software useful.
- Hyeongseok Son, Gunhee Lee, Sunghyun Cho, Seungyong Lee, "Naturalness-Preserving Image Tone Enhancement Using Generative Adversarial Networks", Computer Graphics Form (special issue on Pacific Graphics 2019), Vol. 38, No.7, 2019.
@article{Son19CGF,
author = {Son, Hyeongseok and Lee, Gunhee and Cho, Sunghyun and Lee, Seungyong},
title = {Naturalness-Preserving Image Tone Enhancement Using Generative Adversarial Networks},
journal = {Computer Graphics Forum},
volume = {38},
number = {7},
pages = {277-285},
doi = {10.1111/cgf.13836},
year = {2019}
}
Project ‘COUPE’ aims to develop software that evaluates and improves the quality of images and videos based on big visual data. To achieve the goal, we extract sharpness, color, composition features from images and develop technologies for restoring and improving by using it. In addition, personalization technology through user preference analysis is under study.
Please checkout out other Coupe repositories in our Posgraph github organization.