# Single-Image HDR Reconstruction by Multi-Exposure Generation

arXiv: https://arxiv.org/abs/2210.15897 · HTML: https://mlsanity.com/paper/2210.15897/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 52 references that are in the map.
- First posted on arXiv 28 Oct 2022.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Unprocessing Images for Learned Raw Denoising](https://mlsanity.com/paper/1811.11127/) (2018)
- [CycleISP: Real Image Restoration via Improved Data Synthesis](https://mlsanity.com/paper/2003.07761/) (2020)
- [HDR image reconstruction from a single exposure using deep CNNs](https://mlsanity.com/paper/1710.07480/) (2017)
- [Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline](https://mlsanity.com/paper/2004.01179/) (2020)
- [Deep High Dynamic Range Imaging with Large Foreground Motions](https://mlsanity.com/paper/1711.08937/) (2017)
- [ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content](https://mlsanity.com/paper/1803.02266/) (2018)
- [HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motions](https://mlsanity.com/paper/2007.01628/) (2020)
- [DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairs](https://mlsanity.com/paper/1712.07384/) (2017)
- [Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Loss](https://mlsanity.com/paper/2005.07335/) (2020)
- [Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize](https://mlsanity.com/paper/1707.02937/) (2017)
- [Image Correction via Deep Reciprocating HDR Transformation](https://mlsanity.com/paper/1804.04371/) (2018)
- [Deep Chain HDRI: Reconstructing a High Dynamic Range Image from a Single Low Dynamic Range Image](https://mlsanity.com/paper/1801.06277/) (2018)
- [FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network](https://mlsanity.com/paper/1912.11463/) (2019)
- [Convolutional Sparse Coding for High Dynamic Range Imaging](https://mlsanity.com/paper/1806.04942/) (2018)
- [UPHDR-GAN: Generative Adversarial Network for High Dynamic Range Imaging with Unpaired Data](https://mlsanity.com/paper/2102.01850/) (2021)
- [Hybrid Loss for Learning Single-Image-based HDR Reconstruction](https://mlsanity.com/paper/1812.07134/) (2018)

## Built on by (most cited first, 20 of 20)

- [Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network](https://mlsanity.com/paper/2405.00244/) (2024)
- [Intrinsic Single-Image HDR Reconstruction](https://mlsanity.com/paper/2409.13803/) (2024)
- [AIM 2025 challenge on Inverse Tone Mapping Report: Methods and Results](https://mlsanity.com/paper/2508.13479/) (2025)
- [Optimizing Illuminant Estimation in Dual-Exposure HDR Imaging](https://mlsanity.com/paper/2403.02449/) (2024)
- [ArtHDR-Net: Perceptually Realistic and Accurate HDR Content Creation](https://mlsanity.com/paper/2309.03827/) (2023)
- [GTA-HDR: A Large-Scale Synthetic Dataset for HDR Image Reconstruction](https://mlsanity.com/paper/2403.17837/) (2024)
- [Lightweight and Fast Real-time Image Enhancement via Decomposition of the Spatial-aware Lookup Tables](https://mlsanity.com/paper/2508.16121/) (2025)
- [HistoHDR-Net: Histogram Equalization for Single LDR to HDR Image Translation](https://mlsanity.com/paper/2402.06692/) (2024)
- [Single-Image HDR Reconstruction Assisted Ghost Suppression and Detail Preservation Network for Multi-Exposure HDR Imaging](https://mlsanity.com/paper/2403.04228/) (2024)
- [Sagiri: Low Dynamic Range Image Enhancement with Generative Diffusion Prior](https://mlsanity.com/paper/2406.09389/) (2024)
- [DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models](https://mlsanity.com/paper/2604.06161/) (2026)
- [Beyond Feature Mapping GAP: Integrating Real HDRTV Priors for Superior SDRTV-to-HDRTV Conversion](https://mlsanity.com/paper/2411.10775/) (2024)
- [Physically Inspired Gaussian Splatting for HDR Novel View Synthesis](https://mlsanity.com/paper/2603.28020/) (2026)
- [High Dynamic Range Imaging via Visual Attention Modules](https://mlsanity.com/paper/2307.14705/) (2023)
- [A Cycle Ride to HDR: Semantics Aware Self-Supervised Framework for Unpaired LDR-to-HDR Image Reconstruction](https://mlsanity.com/paper/2410.15068/) (2024)
- [HDR Reconstruction Boosting with Training-Free and Exposure-Consistent Diffusion](https://mlsanity.com/paper/2602.19706/) (2026)
- [Learning to reconstruct from saturated data: audio declipping and high-dynamic range imaging](https://mlsanity.com/paper/2602.22279/) (2026)
- [Single-Shot HDR Recovery via a Video Diffusion Prior](https://mlsanity.com/paper/2605.11628/) (2026)
- [Bio-SFT: Asymmetric Cortical Guidance and Retinal Adaptation for Robust HDR Reconstruction](https://mlsanity.com/paper/2607.17456/) (2026)
- [Recurrent Dynamic Range Extension](https://mlsanity.com/paper/2609.13135/) (2026)

## Abstract (arXiv)

High dynamic range (HDR) imaging is an indispensable technique in modern photography. Traditional methods focus on HDR reconstruction from multiple images, solving the core problems of image alignment, fusion, and tone mapping, yet having a perfect solution due to ghosting and other visual artifacts in the reconstruction. Recent attempts at single-image HDR reconstruction show a promising alternative: by learning to map pixel values to their irradiance using a neural network, one can bypass the align-and-merge pipeline completely yet still obtain a high-quality HDR image. In this work, we propose a weakly supervised learning method that inverts the physical image formation process for HDR reconstruction via learning to generate multiple exposures from a single image. Our neural network can invert the camera response to reconstruct pixel irradiance before synthesizing multiple exposures and hallucinating details in under- and over-exposed regions from a single input image. To train the network, we propose a representation loss, a reconstruction loss, and a perceptual loss applied on pairs of under- and over-exposure images and thus do not require HDR images for training. Our experiments show that our proposed model can effectively reconstruct HDR images. Our qualitative and quantitative results show that our method achieves state-of-the-art performance on the DrTMO dataset. Our code is available at https://github.com/VinAIResearch/single_image_hdr.