# Hybrid Saturation Restoration for LDR Images of HDR Scenes

arXiv: https://arxiv.org/abs/2111.06038 · HTML: https://mlsanity.com/paper/2111.06038/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 51 references that are in the map.
- First posted on arXiv 11 Nov 2021.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [CycleISP: Real Image Restoration via Improved Data Synthesis](https://mlsanity.com/paper/2003.07761/) (2020)
- [Model-Based Deep Learning](https://mlsanity.com/paper/2012.08405/) (2020)
- [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)
- [Material Recognition in the Wild with the Materials in Context Database](https://mlsanity.com/paper/1412.0623/) (2014)
- [Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Loss](https://mlsanity.com/paper/2005.07335/) (2020)
- [End-to-End Differentiable Learning to HDR Image Synthesis for Multi-exposure Images](https://mlsanity.com/paper/2006.15833/) (2020)
- [Single Image Brightening via Multi-Scale Exposure Fusion with Hybrid Learning](https://mlsanity.com/paper/2007.02042/) (2020)
- [Generation of High Dynamic Range Illumination from a Single Image for the Enhancement of Undesirably Illuminated Images](https://mlsanity.com/paper/1708.00636/) (2017)

## Abstract (arXiv)

There are shadow and highlight regions in a low dynamic range (LDR) image which is captured from a high dynamic range (HDR) scene. It is an ill-posed problem to restore the saturated regions of the LDR image. In this paper, the saturated regions of the LDR image are restored by fusing model-based and data-driven approaches. With such a neural augmentation, two synthetic LDR images are first generated from the underlying LDR image via the model-based approach. One is brighter than the input image to restore the shadow regions and the other is darker than the input image to restore the high-light regions. Both synthetic images are then refined via a novel exposedness aware saturation restoration network (EASRN). Finally, the two synthetic images and the input image are combined together via an HDR synthesis algorithm or a multi-scale exposure fusion algorithm. The proposed algorithm can be embedded in any smart phones or digital cameras to produce an information-enriched LDR image.