# High-Resolution Daytime Translation Without Domain Labels

arXiv: https://arxiv.org/abs/2003.08791 · HTML: https://mlsanity.com/paper/2003.08791/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Mar 2020.

## Built on by (most cited first, 28 of 28)

- [VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization](https://mlsanity.com/paper/2103.16874/) (2021)
- [A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation](https://mlsanity.com/paper/2104.07645/) (2021)
- [High-Resolution Image Harmonization via Collaborative Dual Transformations](https://mlsanity.com/paper/2109.06671/) (2021)
- [Video Autoencoder: self-supervised disentanglement of static 3D structure and motion](https://mlsanity.com/paper/2110.02951/) (2021)
- [CoMoGAN: continuous model-guided image-to-image translation](https://mlsanity.com/paper/2103.06879/) (2021)
- [NightLab: A Dual-level Architecture with Hardness Detection for Segmentation at Night](https://mlsanity.com/paper/2204.05538/) (2022)
- [Weather GAN: Multi-Domain Weather Translation Using Generative Adversarial Networks](https://mlsanity.com/paper/2103.05422/) (2021)
- [MOGAN: Morphologic-structure-aware Generative Learning from a Single Image](https://mlsanity.com/paper/2103.02997/) (2021)
- [Physics-informed Guided Disentanglement in Generative Networks](https://mlsanity.com/paper/2107.14229/) (2021)
- [Towards Robust Event-based Networks for Nighttime via Unpaired Day-to-Night Event Translation](https://mlsanity.com/paper/2407.10703/) (2024)
- [Stay Positive: Non-Negative Image Synthesis for Augmented Reality](https://mlsanity.com/paper/2202.00659/) (2022)
- [Few-shot Font Generation by Learning Style Difference and Similarity](https://mlsanity.com/paper/2301.10008/) (2023)
- [Multi-Curve Translator for High-Resolution Photorealistic Image Translation](https://mlsanity.com/paper/2203.07756/) (2022)
- [Disentangling Random and Cyclic Effects in Time-Lapse Sequences](https://mlsanity.com/paper/2207.01413/) (2022)
- [Time-of-Day Neural Style Transfer for Architectural Photographs](https://mlsanity.com/paper/2209.05800/) (2022)
- [Image-to-Image Translation-based Data Augmentation for Robust EV Charging Inlet Detection](https://mlsanity.com/paper/2112.05290/) (2021)
- [Memory-guided Image De-raining Using Time-Lapse Data](https://mlsanity.com/paper/2201.01883/) (2022)
- [ParGAN: Learning Real Parametrizable Transformations](https://mlsanity.com/paper/2211.04996/) (2022)
- [TimeNeRF: Building Generalizable Neural Radiance Fields across Time from Few-Shot Input Views](https://mlsanity.com/paper/2507.13929/) (2025)
- [Delving into Rectifiers in Style-Based Image Translation](https://mlsanity.com/paper/2111.10546/) (2021)
- [Leveraging in-domain supervision for unsupervised image-to-image translation tasks via multi-stream generators](https://mlsanity.com/paper/2112.15091/) (2021)
- [Residual Aligned: Gradient Optimization for Non-Negative Image Synthesis](https://mlsanity.com/paper/2202.04036/) (2022)
- [Line Search-Based Feature Transformation for Fast, Stable, and Tunable Content-Style Control in Photorealistic Style Transfer](https://mlsanity.com/paper/2210.05996/) (2022)
- [Spectrum-inspired Low-light Image Translation for Saliency Detection](https://mlsanity.com/paper/2303.10145/) (2023)
- [Disentangled Contrastive Image Translation for Nighttime Surveillance](https://mlsanity.com/paper/2307.05038/) (2023)
- [SafePaint: Anti-forensic Image Inpainting with Domain Adaptation](https://mlsanity.com/paper/2404.18136/) (2024)
- [Customize Your Own Paired Data via Few-shot Way](https://mlsanity.com/paper/2405.12490/) (2024)
- [MariData: One-Step Unpaired Image Translation for Maritime Environments](https://mlsanity.com/paper/2606.03246/) (2026)

## Abstract (arXiv)

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/.