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

07/04/2020
by   Chaobing Zheng, et al.
0

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.

READ FULL TEXT

page 1

page 4

page 5

page 6

page 7

page 9

page 10

research
08/01/2018

A Pseudo Multi-Exposure Fusion Method Using Single Image

This paper proposes a novel pseudo multi-exposure image fusion method ba...
research
02/28/2023

A DuMux Framework for Data-Driven Multi-Scale Parametrizations

Presented in this work is a framework for the data-driven determination ...
research
11/22/2021

Model-Based Single Image Deep Dehazing

Model-based single image dehazing algorithms restore images with sharp e...
research
11/11/2021

Hybrid Saturation Restoration for LDR Images of HDR Scenes

There are shadow and highlight regions in a low dynamic range (LDR) imag...
research
12/20/2017

DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairs

We present a novel deep learning architecture for fusing static multi-ex...
research
08/02/2017

Generation of High Dynamic Range Illumination from a Single Image for the Enhancement of Undesirably Illuminated Images

This paper presents an algorithm that enhances undesirably illuminated i...
research
11/10/2021

Multi-Scale Single Image Dehazing Using Laplacian and Gaussian Pyramids

Model driven single image dehazing was widely studied on top of differen...

Please sign up or login with your details

Forgot password? Click here to reset