Laplacian Pyramid Based Convolutional Neural Network for Multi-Exposure Fusion

Yilun Xu; Xingming Wu; Jianhua Wang; Hui Dong; Qiantong Wang; Haosong Yue; Weihai Chen

doi:10.1109/CCDC52312.2021.9602586

Laplacian Pyramid Based Convolutional Neural Network for Multi-Exposure Fusion

Yilun Xu
, Xingming Wu^*
, Jianhua Wang
, Hui Dong
, Qiantong Wang
, Haosong Yue
, Weihai Chen

^*此作品的通讯作者

自动化科学与电气工程学院

Beihang University
Zhejiang University of Technology

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

Multi-exposure fusion (MEF) fuses a bracket of differently exposed low dynamic range images into one high-quality image. Motivated by the classical pyramid based MEF, a Laplacian pyramid based convolutional neural network (CNN) is proposed in this paper to fuse LDR images. The network integrates the multi-resolution fusion and non-linear inference of CNN in a model, maintaining global contrast and the detail in the fusion results. With a coarse-to-fine strategy, we rebuild the results from low-resolution to high-resolution, adding details to coarse fusion results progressively. The proposed network preserves details better than traditional CNN based MEF networks.

源语言	英语
主期刊名	Proceedings of the 33rd Chinese Control and Decision Conference, CCDC 2021
出版商	Institute of Electrical and Electronics Engineers Inc.
页	3555-3559
页数	5
ISBN（电子版）	9781665440899
DOI	https://doi.org/10.1109/CCDC52312.2021.9602586
出版状态	已出版 - 2021
活动	33rd Chinese Control and Decision Conference, CCDC 2021 - Kunming, 中国期限: 22 5月 2021 → 24 5月 2021

出版系列

姓名	Proceedings of the 33rd Chinese Control and Decision Conference, CCDC 2021

会议

会议	33rd Chinese Control and Decision Conference, CCDC 2021
国家/地区	中国
市	Kunming
时期	22/05/21 → 24/05/21

访问文件

10.1109/CCDC52312.2021.9602586

其它文件与链接

链接到 Scopus 的出版物

引用此

Xu, Y., Wu, X., Wang, J., Dong, H., Wang, Q., Yue, H., & Chen, W. (2021). Laplacian Pyramid Based Convolutional Neural Network for Multi-Exposure Fusion. 在 Proceedings of the 33rd Chinese Control and Decision Conference, CCDC 2021 (页码 3555-3559). (Proceedings of the 33rd Chinese Control and Decision Conference, CCDC 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CCDC52312.2021.9602586

@inproceedings{6680b28b57274efdb4dfec9c064c59c3,

title = "Laplacian Pyramid Based Convolutional Neural Network for Multi-Exposure Fusion",

abstract = "Multi-exposure fusion (MEF) fuses a bracket of differently exposed low dynamic range images into one high-quality image. Motivated by the classical pyramid based MEF, a Laplacian pyramid based convolutional neural network (CNN) is proposed in this paper to fuse LDR images. The network integrates the multi-resolution fusion and non-linear inference of CNN in a model, maintaining global contrast and the detail in the fusion results. With a coarse-to-fine strategy, we rebuild the results from low-resolution to high-resolution, adding details to coarse fusion results progressively. The proposed network preserves details better than traditional CNN based MEF networks.",

keywords = "CNN, Coarse-to-Fine, Laplacian Pyramid, Multi-exposure Fusion, Residual Learning",

author = "Yilun Xu and Xingming Wu and Jianhua Wang and Hui Dong and Qiantong Wang and Haosong Yue and Weihai Chen",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 33rd Chinese Control and Decision Conference, CCDC 2021 ; Conference date: 22-05-2021 Through 24-05-2021",

year = "2021",

doi = "10.1109/CCDC52312.2021.9602586",

language = "英语",

series = "Proceedings of the 33rd Chinese Control and Decision Conference, CCDC 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "3555--3559",

booktitle = "Proceedings of the 33rd Chinese Control and Decision Conference, CCDC 2021",

address = "美国",

}

Xu, Y, Wu, X, Wang, J, Dong, H, Wang, Q, Yue, H & Chen, W 2021, Laplacian Pyramid Based Convolutional Neural Network for Multi-Exposure Fusion. 在 Proceedings of the 33rd Chinese Control and Decision Conference, CCDC 2021. Proceedings of the 33rd Chinese Control and Decision Conference, CCDC 2021, Institute of Electrical and Electronics Engineers Inc., 页码 3555-3559, 33rd Chinese Control and Decision Conference, CCDC 2021, Kunming, 中国, 22/05/21. https://doi.org/10.1109/CCDC52312.2021.9602586

Laplacian Pyramid Based Convolutional Neural Network for Multi-Exposure Fusion. / Xu, Yilun; Wu, Xingming; Wang, Jianhua 等.
Proceedings of the 33rd Chinese Control and Decision Conference, CCDC 2021. Institute of Electrical and Electronics Engineers Inc., 2021. 页码 3555-3559 (Proceedings of the 33rd Chinese Control and Decision Conference, CCDC 2021).

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

TY - GEN

T1 - Laplacian Pyramid Based Convolutional Neural Network for Multi-Exposure Fusion

AU - Xu, Yilun

AU - Wu, Xingming

AU - Wang, Jianhua

AU - Dong, Hui

AU - Wang, Qiantong

AU - Yue, Haosong

AU - Chen, Weihai

PY - 2021

Y1 - 2021

N2 - Multi-exposure fusion (MEF) fuses a bracket of differently exposed low dynamic range images into one high-quality image. Motivated by the classical pyramid based MEF, a Laplacian pyramid based convolutional neural network (CNN) is proposed in this paper to fuse LDR images. The network integrates the multi-resolution fusion and non-linear inference of CNN in a model, maintaining global contrast and the detail in the fusion results. With a coarse-to-fine strategy, we rebuild the results from low-resolution to high-resolution, adding details to coarse fusion results progressively. The proposed network preserves details better than traditional CNN based MEF networks.

AB - Multi-exposure fusion (MEF) fuses a bracket of differently exposed low dynamic range images into one high-quality image. Motivated by the classical pyramid based MEF, a Laplacian pyramid based convolutional neural network (CNN) is proposed in this paper to fuse LDR images. The network integrates the multi-resolution fusion and non-linear inference of CNN in a model, maintaining global contrast and the detail in the fusion results. With a coarse-to-fine strategy, we rebuild the results from low-resolution to high-resolution, adding details to coarse fusion results progressively. The proposed network preserves details better than traditional CNN based MEF networks.

KW - CNN

KW - Coarse-to-Fine

KW - Laplacian Pyramid

KW - Multi-exposure Fusion

KW - Residual Learning

UR - https://www.scopus.com/pages/publications/85125179421

U2 - 10.1109/CCDC52312.2021.9602586

DO - 10.1109/CCDC52312.2021.9602586

M3 - 会议稿件

AN - SCOPUS:85125179421

T3 - Proceedings of the 33rd Chinese Control and Decision Conference, CCDC 2021

SP - 3555

EP - 3559

BT - Proceedings of the 33rd Chinese Control and Decision Conference, CCDC 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 33rd Chinese Control and Decision Conference, CCDC 2021

Y2 - 22 May 2021 through 24 May 2021

ER -

Xu Y, Wu X, Wang J, Dong H, Wang Q, Yue H 等. Laplacian Pyramid Based Convolutional Neural Network for Multi-Exposure Fusion. 在 Proceedings of the 33rd Chinese Control and Decision Conference, CCDC 2021. Institute of Electrical and Electronics Engineers Inc. 2021. 页码 3555-3559. (Proceedings of the 33rd Chinese Control and Decision Conference, CCDC 2021). doi: 10.1109/CCDC52312.2021.9602586

Laplacian Pyramid Based Convolutional Neural Network for Multi-Exposure Fusion

摘要

出版系列

会议

访问文件

其它文件与链接

指纹

引用此