# Frequency Domain Loss Function for Deep Exposure Correction of Dark Images

arXiv: https://arxiv.org/abs/2104.10856 · HTML: https://mlsanity.com/paper/2104.10856/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 44 references that are in the map.
- First posted on arXiv 22 Apr 2021.

## Builds on (most cited first, 18 of 18)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better](https://mlsanity.com/paper/1908.03826/) (2019)
- [LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement](https://mlsanity.com/paper/1511.03995/) (2015)
- [Getting to Know Low-light Images with The Exclusively Dark Dataset](https://mlsanity.com/paper/1805.11227/) (2018)
- [Image Inpainting with Learnable Bidirectional Attention Maps](https://mlsanity.com/paper/1909.00968/) (2019)
- [Handheld Mobile Photography in Very Low Light](https://mlsanity.com/paper/1910.11336/) (2019)
- [MSR-net:Low-light Image Enhancement Using Deep Convolutional Network](https://mlsanity.com/paper/1711.02488/) (2017)
- [ViDeNN: Deep Blind Video Denoising](https://mlsanity.com/paper/1904.10898/) (2019)
- [A practical guide and software for analysing pairwise comparison experiments](https://mlsanity.com/paper/1712.03686/) (2017)
- [Learning Digital Camera Pipeline for Extreme Low-Light Imaging](https://mlsanity.com/paper/1904.05939/) (2019)
- [Color-wise Attention Network for Low-light Image Enhancement](https://mlsanity.com/paper/1911.08681/) (2019)

## Built on by (most cited first, 4 of 4)

- [MTKD: Multi-Teacher Knowledge Distillation for Image Super-Resolution](https://mlsanity.com/paper/2404.09571/) (2024)
- [Wavelet-based Loss for High-frequency Interface Dynamics](https://mlsanity.com/paper/2209.02316/) (2022)
- [Bidirectional Image-Event Guided Fusion Framework for Low-Light Image Enhancement](https://mlsanity.com/paper/2506.06120/) (2025)
- [Luminance Component Analysis for Exposure Correction](https://mlsanity.com/paper/2411.16325/) (2024)

## Abstract (arXiv)

We address the problem of exposure correction of dark, blurry and noisy images captured in low-light conditions in the wild. Classical image-denoising filters work well in the frequency space but are constrained by several factors such as the correct choice of thresholds, frequency estimates etc. On the other hand, traditional deep networks are trained end-to-end in the RGB space by formulating this task as an image-translation problem. However, that is done without any explicit constraints on the inherent noise of the dark images and thus produce noisy and blurry outputs. To this end we propose a DCT/FFT based multi-scale loss function, which when combined with traditional losses, trains a network to translate the important features for visually pleasing output. Our loss function is end-to-end differentiable, scale-agnostic, and generic; i.e., it can be applied to both RAW and JPEG images in most existing frameworks without additional overhead. Using this loss function, we report significant improvements over the state-of-the-art using quantitative metrics and subjective tests.