# No Fear of the Dark: Image Retrieval under Varying Illumination Conditions

arXiv: https://arxiv.org/abs/1908.08999 · HTML: https://mlsanity.com/paper/1908.08999/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2019.

## Built on by (most cited first, 12 of 12)

- [DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation](https://mlsanity.com/paper/2104.10834/) (2021)
- [Zero-Shot Day-Night Domain Adaptation with a Physics Prior](https://mlsanity.com/paper/2108.05137/) (2021)
- [ILIAS: Instance-Level Image retrieval At Scale](https://mlsanity.com/paper/2502.11748/) (2025)
- [Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments](https://mlsanity.com/paper/2210.16046/) (2022)
- [Learning Semantics for Visual Place Recognition through Multi-Scale Attention](https://mlsanity.com/paper/2201.09701/) (2022)
- [Similarity Min-Max: Zero-Shot Day-Night Domain Adaptation](https://mlsanity.com/paper/2307.08779/) (2023)
- [Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes](https://mlsanity.com/paper/2109.03585/) (2021)
- [Self-Aligned Concave Curve: Illumination Enhancement for Unsupervised Adaptation](https://mlsanity.com/paper/2210.03792/) (2022)
- [Dark Side Augmentation: Generating Diverse Night Examples for Metric Learning](https://mlsanity.com/paper/2309.16351/) (2023)
- [Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matching](https://mlsanity.com/paper/2512.12610/) (2025)
- [Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency](https://mlsanity.com/paper/2402.09237/) (2024)
- [PICS: Pipeline for Image Captioning and Search](https://mlsanity.com/paper/2402.10090/) (2024)

## Abstract (arXiv)

Image retrieval under varying illumination conditions, such as day and night images, is addressed by image preprocessing, both hand-crafted and learned. Prior to extracting image descriptors by a convolutional neural network, images are photometrically normalised in order to reduce the descriptor sensitivity to illumination changes. We propose a learnable normalisation based on the U-Net architecture, which is trained on a combination of single-camera multi-exposure images and a newly constructed collection of similar views of landmarks during day and night. We experimentally show that both hand-crafted normalisation based on local histogram equalisation and the learnable normalisation outperform standard approaches in varying illumination conditions, while staying on par with the state-of-the-art methods on daylight illumination benchmarks, such as Oxford or Paris datasets.