mlsanityData to 14 Oct 2026

High-Resolution Daytime Translation Without Domain Labels

arXiv 2003.08791 ↗First posted 19 Mar 2020cs.CV cs.LG eess.IVcited by 28

Not on the map. Why?

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/.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 9; 2023: 3; 2024: 3; 2025: 1; 2026: 1.

28 papers.

Sort:

  1. 2021VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalizationcited by 287
  2. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 114
  3. 2021High-Resolution Image Harmonization via Collaborative Dual Transformationscited by 55
  4. 2021Video Autoencoder: self-supervised disentanglement of static 3D structure and motioncited by 34
  5. 2021CoMoGAN: continuous model-guided image-to-image translationcited by 27
  6. 2022NightLab: A Dual-level Architecture with Hardness Detection for Segmentation at Nightcited by 21
  7. 2021Weather GAN: Multi-Domain Weather Translation Using Generative Adversarial Networkscited by 18
  8. 2021MOGAN: Morphologic-structure-aware Generative Learning from a Single Imagecited by 9
  9. 2021Physics-informed Guided Disentanglement in Generative Networkscited by 9
  10. 2024Towards Robust Event-based Networks for Nighttime via Unpaired Day-to-Night Event Translationcited by 9
  11. 2022Stay Positive: Non-Negative Image Synthesis for Augmented Realitycited by 4
  12. 2023Few-shot Font Generation by Learning Style Difference and Similaritycited by 4
16 more
  1. 2022Multi-Curve Translator for High-Resolution Photorealistic Image Translationcited by 3
  2. 2022Disentangling Random and Cyclic Effects in Time-Lapse Sequencescited by 3
  3. 2022Time-of-Day Neural Style Transfer for Architectural Photographscited by 3
  4. 2021Image-to-Image Translation-based Data Augmentation for Robust EV Charging Inlet Detectioncited by 2
  5. 2022Memory-guided Image De-raining Using Time-Lapse Datacited by 2
  6. 2022ParGAN: Learning Real Parametrizable Transformationscited by 1
  7. 2025TimeNeRF: Building Generalizable Neural Radiance Fields across Time from Few-Shot Input Viewscited by 1
  8. 2021Delving into Rectifiers in Style-Based Image Translationcited by 0
  9. 2021Leveraging in-domain supervision for unsupervised image-to-image translation tasks via multi-stream generatorscited by 0
  10. 2022Residual Aligned: Gradient Optimization for Non-Negative Image Synthesiscited by 0
  11. 2022Line Search-Based Feature Transformation for Fast, Stable, and Tunable Content-Style Control in Photorealistic Style Transfercited by 0
  12. 2023Spectrum-inspired Low-light Image Translation for Saliency Detectioncited by 0
  13. 2023Disentangled Contrastive Image Translation for Nighttime Surveillancecited by 0
  14. 2024SafePaint: Anti-forensic Image Inpainting with Domain Adaptationcited by 0
  15. 2024Customize Your Own Paired Data via Few-shot Waycited by 0
  16. 2026MariData: One-Step Unpaired Image Translation for Maritime Environmentscited by 0