# Unsupervised HDR Image and Video Tone Mapping via Contrastive Learning

arXiv: https://arxiv.org/abs/2303.07327 · HTML: https://mlsanity.com/paper/2303.07327/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 92 references that are in the map.
- First posted on arXiv 13 Mar 2023.

## Builds on (most cited first, 26 of 26)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [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)
- [Learning Blind Video Temporal Consistency](https://mlsanity.com/paper/1808.00449/) (2018)
- [Contrastive Learning for Compact Single Image Dehazing](https://mlsanity.com/paper/2104.09367/) (2021)
- [Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation](https://mlsanity.com/paper/2103.00860/) (2021)
- [Vision GNN: An Image is Worth Graph of Nodes](https://mlsanity.com/paper/2206.00272/) (2022)
- [Unsupervised Degradation Representation Learning for Blind Super-Resolution](https://mlsanity.com/paper/2104.00416/) (2021)
- [FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation](https://mlsanity.com/paper/1907.01361/) (2019)
- [Unpaired Deep Image Deraining Using Dual Contrastive Learning](https://mlsanity.com/paper/2109.02973/) (2021)
- [HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset](https://mlsanity.com/paper/2103.14943/) (2021)
- [Deep Learning for HDR Imaging: State-of-the-Art and Future Trends](https://mlsanity.com/paper/2110.10394/) (2021)
- [WESPE: Weakly Supervised Photo Enhancer for Digital Cameras](https://mlsanity.com/paper/1709.01118/) (2017)
- [Dual Contrastive Loss and Attention for GANs](https://mlsanity.com/paper/2103.16748/) (2021)
- [Deep Tone Mapping Operator for High Dynamic Range Images](https://mlsanity.com/paper/1908.04197/) (2019)
- [FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network](https://mlsanity.com/paper/1912.11463/) (2019)
- [LIME: A Method for Low-light IMage Enhancement](https://mlsanity.com/paper/1605.05034/) (2016)
- [Real-time Streaming Video Denoising with Bidirectional Buffers](https://mlsanity.com/paper/2207.06937/) (2022)
- [Single Underwater Image Restoration by Contrastive Learning](https://mlsanity.com/paper/2103.09697/) (2021)
- [Unpaired Learning for High Dynamic Range Image Tone Mapping](https://mlsanity.com/paper/2111.00219/) (2021)
- [Perceptually Optimized Deep High-Dynamic-Range Image Tone Mapping](https://mlsanity.com/paper/2109.00180/) (2021)
- [Real-time Tone Mapping: A State of the Art Report](https://mlsanity.com/paper/2003.03074/) (2020)

## Built on by (most cited first, 6 of 6)

- [UltraFusion: Ultra High Dynamic Imaging using Exposure Fusion](https://mlsanity.com/paper/2501.11515/) (2025)
- [Locality-aware Cross-modal Correspondence Learning for Dense Audio-Visual Events Localization](https://mlsanity.com/paper/2409.07967/) (2024)
- [Learning Adaptive Lighting via Channel-Aware Guidance](https://mlsanity.com/paper/2412.01493/) (2024)
- [Learning Differential Pyramid Representation for Tone Mapping](https://mlsanity.com/paper/2412.01463/) (2024)
- [Normalized Iterative Hard Thresholding for Tensor Recovery](https://mlsanity.com/paper/2507.04228/) (2025)
- [Modulo Video Recovery via Selective Spatiotemporal Vision Transformer](https://mlsanity.com/paper/2511.07479/) (2025)

## Abstract (arXiv)

Capturing high dynamic range (HDR) images (videos) is attractive because it can reveal the details in both dark and bright regions. Since the mainstream screens only support low dynamic range (LDR) content, tone mapping algorithm is required to compress the dynamic range of HDR images (videos). Although image tone mapping has been widely explored, video tone mapping is lagging behind, especially for the deep-learning-based methods, due to the lack of HDR-LDR video pairs. In this work, we propose a unified framework (IVTMNet) for unsupervised image and video tone mapping. To improve unsupervised training, we propose domain and instance based contrastive learning loss. Instead of using a universal feature extractor, such as VGG to extract the features for similarity measurement, we propose a novel latent code, which is an aggregation of the brightness and contrast of extracted features, to measure the similarity of different pairs. We totally construct two negative pairs and three positive pairs to constrain the latent codes of tone mapped results. For the network structure, we propose a spatial-feature-enhanced (SFE) module to enable information exchange and transformation of nonlocal regions. For video tone mapping, we propose a temporal-feature-replaced (TFR) module to efficiently utilize the temporal correlation and improve the temporal consistency of video tone-mapped results. We construct a large-scale unpaired HDR-LDR video dataset to facilitate the unsupervised training process for video tone mapping. Experimental results demonstrate that our method outperforms state-of-the-art image and video tone mapping methods. Our code and dataset are available at https://github.com/cao-cong/UnCLTMO.