# HDRVideo-GAN: Deep Generative HDR Video Reconstruction

arXiv: https://arxiv.org/abs/2110.11795 · HTML: https://mlsanity.com/paper/2110.11795/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 58 references that are in the map.
- First posted on arXiv 22 Oct 2021.

## Builds on (most cited first, 20 of 20)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [Optical Flow Estimation using a Spatial Pyramid Network](https://mlsanity.com/paper/1611.00850/) (2016)
- [HDR image reconstruction from a single exposure using deep CNNs](https://mlsanity.com/paper/1710.07480/) (2017)
- [High-Quality Self-Supervised Deep Image Denoising](https://mlsanity.com/paper/1901.10277/) (2019)
- [ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content](https://mlsanity.com/paper/1803.02266/) (2018)
- [A Style-Aware Content Loss for Real-time HD Style Transfer](https://mlsanity.com/paper/1807.10201/) (2018)
- [Self-Supervised Feature Learning by Learning to Spot Artifacts](https://mlsanity.com/paper/1806.05024/) (2018)
- [Learning High Dynamic Range from Outdoor Panoramas](https://mlsanity.com/paper/1703.10200/) (2017)
- [Lipschitz Generative Adversarial Nets](https://mlsanity.com/paper/1902.05687/) (2019)
- [Single-frame Regularization for Temporally Stable CNNs](https://mlsanity.com/paper/1902.10424/) (2019)
- [A Unified Framework for Multi-Sensor HDR Video Reconstruction](https://mlsanity.com/paper/1308.4908/) (2013)
- [Locally Non-rigid Registration for Mobile HDR Photography](https://mlsanity.com/paper/1504.01441/) (2015)
- [Automatic Temporally Coherent Video Colorization](https://mlsanity.com/paper/1904.09527/) (2019)
- [ProFlow: Learning to Predict Optical Flow](https://mlsanity.com/paper/1806.00800/) (2018)
- [A Maximum A Posteriori Estimation Framework for Robust High Dynamic Range Video Synthesis](https://mlsanity.com/paper/1612.02761/) (2016)

## Built on by (most cited first, 3 of 3)

- [ArtHDR-Net: Perceptually Realistic and Accurate HDR Content Creation](https://mlsanity.com/paper/2309.03827/) (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)
- [Generating HDR Video from SDR Video](https://mlsanity.com/paper/2605.14703/) (2026)

## Abstract (arXiv)

High dynamic range (HDR) videos provide a more visually realistic experience than the standard low dynamic range (LDR) videos. Despite having significant progress in HDR imaging, it is still a challenging task to capture high-quality HDR video with a conventional off-the-shelf camera. Existing approaches rely entirely on using dense optical flow between the neighboring LDR sequences to reconstruct an HDR frame. However, they lead to inconsistencies in color and exposure over time when applied to alternating exposures with noisy frames. In this paper, we propose an end-to-end GAN-based framework for HDR video reconstruction from LDR sequences with alternating exposures. We first extract clean LDR frames from noisy LDR video with alternating exposures with a denoising network trained in a self-supervised setting. Using optical flow, we then align the neighboring alternating-exposure frames to a reference frame and then reconstruct high-quality HDR frames in a complete adversarial setting. To further improve the robustness and quality of generated frames, we incorporate temporal stability-based regularization term along with content and style-based losses in the cost function during the training procedure. Experimental results demonstrate that our framework achieves state-of-the-art performance and generates superior quality HDR frames of a video over the existing methods.