# High-Resolution Daytime Translation Without Domain Labels

Source: [High-Resolution Daytime Translation Without Domain Labels](<https://www.sota2.com/research/paper/68fa7c061e209131cea8bf33>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T07:04:32.834Z

Authors: Ivan Anokhin, Pavel Solovev, Denis Korzhenkov, Alexey Kharlamov, Taras Khakhulin, Alexey Silvestrov, Sergey Nikolenko, Victor Lempitsky, Gleb Sterkin

Published: 2020-03-19T13:59:31.000Z

## 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. Our results are available at https://saic-mdal.github.io/HiDT/.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Harmonization on HAdobe5k iHarmony4 (test)](<https://www.sota2.com/research/sota/image-harmonization-on-hadobe5k-iharmony4-test.md>): Image Harmonization; HAdobe5k iHarmony4 (test); MSE: 265.32.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2003.08791>)

[PDF](<https://arxiv.org/pdf/2003.08791.pdf>)