End-to-End Exposure Fusion Using Convolutional Neural Network

Jinhua WANG  Weiqiang WANG  Guangmei XU  Hongzhe LIU  

IEICE TRANSACTIONS on Information and Systems   Vol.E101-D   No.2   pp.560-563
Publication Date: 2018/02/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2017EDL8173
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
exposure fusion,  convolutional neural networks,  fusion rule,  activity level measurement,  

Full Text: PDF(635.3KB)>>
Buy this Article

In this paper, we describe the direct learning of an end-to-end mapping between under-/over-exposed images and well-exposed images. The mapping is represented as a deep convolutional neural network (CNN) that takes multiple-exposure images as input and outputs a high-quality image. Our CNN has a lightweight structure, yet gives state-of-the-art fusion quality. Furthermore, we know that for a given pixel, the influence of the surrounding pixels gradually increases as the distance decreases. If the only pixels considered are those in the convolution kernel neighborhood, the final result will be affected. To overcome this problem, the size of the convolution kernel is often increased. However, this also increases the complexity of the network (too many parameters) and the training time. In this paper, we present a method in which a number of sub-images of the source image are obtained using the same CNN model, providing more neighborhood information for the convolution operation. Experimental results demonstrate that the proposed method achieves better performance in terms of both objective evaluation and visual quality.