# Unpaired Learning for High Dynamic Range Image Tone Mapping

arXiv: https://arxiv.org/abs/2111.00219 · HTML: https://mlsanity.com/paper/2111.00219/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 57 references that are in the map.
- First posted on arXiv 30 Oct 2021.

## Builds on (most cited first, 13 of 13)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017)
- [Deep Semantic Face Deblurring](https://mlsanity.com/paper/1803.03345/) (2018)
- [Deep Tone Mapping Operator for High Dynamic Range Images](https://mlsanity.com/paper/1908.04197/) (2019)
- [Deep Feature Consistent Deep Image Transformations: Downscaling, Decolorization and HDR Tone Mapping](https://mlsanity.com/paper/1707.09482/) (2017)

## Built on by (most cited first, 11 of 11)

- [Learning to Adapt to Light](https://mlsanity.com/paper/2202.08098/) (2022)
- [UltraFusion: Ultra High Dynamic Imaging using Exposure Fusion](https://mlsanity.com/paper/2501.11515/) (2025)
- [Learning Diverse Tone Styles for Image Retouching](https://mlsanity.com/paper/2207.05430/) (2022)
- [Unsupervised HDR Image and Video Tone Mapping via Contrastive Learning](https://mlsanity.com/paper/2303.07327/) (2023)
- [Towards Real World HDRTV Reconstruction: A Data Synthesis-based Approach](https://mlsanity.com/paper/2211.03058/) (2022)
- [Discovering an Image-Adaptive Coordinate System for Photography Processing](https://mlsanity.com/paper/2501.06448/) (2025)
- [A Perceptually Optimized and Self-Calibrated Tone Mapping Operator](https://mlsanity.com/paper/2206.09146/) (2022)
- [Rendering Nighttime Image Via Cascaded Color and Brightness Compensation](https://mlsanity.com/paper/2204.08970/) (2022)
- [Unsupervised Learning Based Multi-Scale Exposure Fusion](https://mlsanity.com/paper/2409.17830/) (2024)
- [A Cycle Ride to HDR: Semantics Aware Self-Supervised Framework for Unpaired LDR-to-HDR Image Reconstruction](https://mlsanity.com/paper/2410.15068/) (2024)
- [Neural Block-wise Auto-exposure for Single-Shot High Dynamic Range Imaging](https://mlsanity.com/paper/2610.18733/) (2026)

## Abstract (arXiv)

High dynamic range (HDR) photography is becoming increasingly popular and available by DSLR and mobile-phone cameras. While deep neural networks (DNN) have greatly impacted other domains of image manipulation, their use for HDR tone-mapping is limited due to the lack of a definite notion of ground-truth solution, which is needed for producing training data. In this paper we describe a new tone-mapping approach guided by the distinct goal of producing low dynamic range (LDR) renditions that best reproduce the visual characteristics of native LDR images. This goal enables the use of an unpaired adversarial training based on unrelated sets of HDR and LDR images, both of which are widely available and easy to acquire. In order to achieve an effective training under this minimal requirements, we introduce the following new steps and components: (i) a range-normalizing pre-process which estimates and applies a different level of curve-based compression, (ii) a loss that preserves the input content while allowing the network to achieve its goal, and (iii) the use of a more concise discriminator network, designed to promote the reproduction of low-level attributes native LDR possess. Evaluation of the resulting network demonstrates its ability to produce photo-realistic artifact-free tone-mapped images, and state-of-the-art performance on different image fidelity indices and visual distances.