Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Journal article
Title: Ghost removal via channel attention in exposure fusion
Author: Yan, Q.
Wang, B.
Li, P.
Li, X.
Zhang, A.
Shi, Q.
You, Z.
Zhu, Y.
Sun, J.
Zhang, Y.
Citation: Computer Vision and Image Understanding, 2020; 201:1-8
Publisher: Elsevier
Issue Date: 2020
ISSN: 1077-3142
Statement of
Qingsen Yan, Bo Wang, Peipei Li, Xianjun Li, Ao Zhang, Qinfeng Shi
Abstract: High dynamic range (HDR) imaging is to reconstruct high-quality images with a broad range of illuminations from a set of differently exposed images. Some existing algorithms align the input images before merging them into an HDR image, but artifacts of the registration appear due to misalignment. Recent works try to remove the ghosts by detecting motion region or skipping the registered process, however, the result still suffers from ghost artifacts for scenes with significant motions. In this paper, we propose a novel Multi-scale Channel Attention guided Network (MCANet) to address the ghosting problem. We use multi-scale blocks consisting of dilated convolution layers to extract informative features. The channel attention blocks suppress undesired components and guide the network to refine features to make full use of feature maps. The proposed MCANet recovers the occluded or saturated details and reduces artifacts due to misalignment. Experiments show that the proposed MCANet can achieve state-of-the-art quantitative and qualitative results.
Keywords: High dynamic range; multiple exposed images; de-ghosting; image fusion; convolution neural network
Rights: © 2020 Elsevier Inc.
DOI: 10.1016/j.cviu.2020.103079
Grant ID:
Published version:
Appears in Collections:Aurora harvest 8
Electrical and Electronic Engineering publications

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.