High-Resolution Daytime Translation Without Domain Labels

Ivan Anokhin, Pavel Solovev, Denis Korzhenkov, Alexey Kharlamov, Taras Khakhulin, Aleksei Silvestrov, Sergey Nikolenko, Victor Lempitsky, Gleb Sterkin; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 7488-7497

Abstract

Modeling daytime changes in high resolution photographs, e.g., re-rendering the same scene under different illuminations typical for day, night, or dawn, is a challenging image manipulation task. We present the high-resolution daytime translation (HiDT) model for this task. HiDT combines a generative image-to-image model and a new upsampling scheme that allows to apply image translation at high resolution. The model demonstrates competitive results in terms of both commonly used GAN metrics and human evaluation. Importantly, this good performance comes as a result of training on a dataset of still landscape images with no daytime labels available.

Related Material

[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Anokhin_2020_CVPR,
author = {Anokhin, Ivan and Solovev, Pavel and Korzhenkov, Denis and Kharlamov, Alexey and Khakhulin, Taras and Silvestrov, Aleksei and Nikolenko, Sergey and Lempitsky, Victor and Sterkin, Gleb},
title = {High-Resolution Daytime Translation Without Domain Labels},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}