# Single Image Brightening via Multi-Scale Exposure Fusion with Hybrid Learning

arXiv: https://arxiv.org/abs/2007.02042 · HTML: https://mlsanity.com/paper/2007.02042/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jul 2020.

## Built on by (most cited first, 12 of 12)

- [Deep Joint Demosaicing and High Dynamic Range Imaging within a Single Shot](https://mlsanity.com/paper/2111.07281/) (2021)
- [Dual-Scale Single Image Dehazing Via Neural Augmentation](https://mlsanity.com/paper/2209.05913/) (2022)
- [Probabilistic Spatial Distribution Prior Based Attentional Keypoints Matching Network](https://mlsanity.com/paper/2111.09006/) (2021)
- [Online Unsupervised Video Object Segmentation via Contrastive Motion Clustering](https://mlsanity.com/paper/2306.12048/) (2023)
- [Novel Intensity Mapping Functions: Weighted Histogram Averaging](https://mlsanity.com/paper/2111.07283/) (2021)
- [FCNet: A Convolutional Neural Network for Arbitrary-Length Exposure Estimation](https://mlsanity.com/paper/2203.03624/) (2022)
- [Single image dehazing via combining the prior knowledge and CNNs](https://mlsanity.com/paper/2111.05701/) (2021)
- [Hybrid Saturation Restoration for LDR Images of HDR Scenes](https://mlsanity.com/paper/2111.06038/) (2021)
- [Low-light Image and Video Enhancement via Selective Manipulation of Chromaticity](https://mlsanity.com/paper/2203.04889/) (2022)
- [Single Image Deraining via Feature-based Deep Convolutional Neural Network](https://mlsanity.com/paper/2305.02100/) (2023)
- [CNN Injected Transformer for Image Exposure Correction](https://mlsanity.com/paper/2309.04366/) (2023)
- [Neural Block-wise Auto-exposure for Single-Shot High Dynamic Range Imaging](https://mlsanity.com/paper/2610.18733/) (2026)

## Abstract (arXiv)

A small ISO and a small exposure time are usually used to capture an image in the back or low light conditions which results in an image with negligible motion blur and small noise but look dark. In this paper, a single image brightening algorithm is introduced to brighten such an image. The proposed algorithm includes a unique hybrid learning framework to generate two virtual images with large exposure times. The virtual images are first generated via intensity mapping functions (IMFs) which are computed using camera response functions (CRFs) and this is a model-driven approach. Both the virtual images are then enhanced by using a data-driven approach, i.e. a residual convolutional neural network to approach the ground truth images. The model-driven approach and the data-driven one compensate each other in the proposed hybrid learning framework. The final brightened image is obtained by fusing the original image and two virtual images via a multi-scale exposure fusion algorithm with properly defined weights. Experimental results show that the proposed brightening algorithm outperforms existing algorithms in terms of the MEF-SSIM metric.