arrow
返回

High dynamic range imaging via gradient-aware context aggregation network

delete2022-02-01
delete23
PRE
AI
Q
Qingsen Yan
D
Dong Gong *
Q
Qinfeng Shi
A
Anton van den Hengel
J
Jinqiu Sun
Y
Yu Zhu
Y
Yanning Zhang
DOI:10.1016/j.patcog.2021.108342delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Obtaining a high dynamic range (HDR) image from multiple low dynamic range images with different ex-posures is an important step in various computer vision tasks. One of the ongoing challenges in the field is to generate HDR images without ghosting artifacts. Motivated by an observation that such artifacts are particularly noticeable in the gradient domain, in this paper, we propose an HDR imaging approach that aggregates the information from multiple LDR images with guidance from image gradient domain. The proposed method generates artifact-free images by integrating the image gradient information and the image context information in the pixel domain. The context information in a large area helps to re-construct the contents contaminated by saturation and misalignments. Specifically, an additional gradient stream and the supervision in the gradient domain are applied to incorporate the gradient information in HDR imaging. To use the context information captured from a large area while preserving spatial resolu-tion, we adopt dilated convolutions to extract multi-scale features with rich context information. More -over, we build a new dataset containing 40 groups of real-world images from diverse scenes with ground truth to validate the proposed model. The samples in the proposed dataset include more challenging moving objects inducing misalignments. Extensive experimental results demonstrate that our proposed model outperforms previous methods on different datasets in terms of both quantitative measure and visual perception quality. (c) 2021 Elsevier Ltd. All rights reserved.
Keyword:
High dynamic range imaging
Deep learning
Exposure fusion
Ghosting artifacts
Image gradients

期刊

Pattern Recognition 封面图
Pattern Recognition
IF:
7.6
论文数:
1.3W
被引数:
4.5W

机构

U
University of Adelaide
学者数:
2.3W
论文数: 2.4W
被引数: 4.2W
N
Northwestern Polytechnical University
学者数:
4.6W
论文数: 3.7W
被引数: 5.3W
引用论文

引用论文

The application of synchrotron micro-computed tomography to characterize the three-dimensional microstructure in irradiated nuclear fuel
err2020-08-01
err0
errOAAI
errJonova Thomas; Alejandro Figueroa Bengoa; Sri Tapaswi Nori; Ran Ren; Peter Kenesei; Jon Almer; James Hunter; Jason Harp; Maria A. Okuniewski
err分享
err收藏
Biomechanical parameters on body segments of Korean adults
err1999-01-01
err0
PREAI
errSe Jin Park; Soo Chan Park; Jin Ho Kim; Chae-Bogk Kim
err分享
err收藏
Towards accurate HDR imaging with learning generator constraints
err2021-03-01
err12
errOAAI
errYan, Qingsen; Wang, Bo; Zhang, Lei; Zhang, Jingyu; You, Zheng; Shi, Qinfeng; Zhang, Yanning
err分享
err收藏
err分享
err收藏
err分享
err收藏
A new design in iterative image deblurring for improved robustness and performance
err2019-06-01
err10
errOAAI
errLi, Taihao; Chen, Huai; Zhang, Min; Liu, Shupeng; Xia, Shunren; Cao, Xinhua; Young, Geoffrey S.; Xu, Xiaoyin
err分享
err收藏
学者 查看更多内容