基于pix2pix网络结构的单曝光HDR图像生成方法

doi:10.3778/j.issn.1002-8331.2101-0126

计算机工程与应用 ›› 2022, Vol. 58 ›› Issue (16): 242-248.DOI: 10.3778/j.issn.1002-8331.2101-0126

基于pix2pix网络结构的单曝光HDR图像生成方法

张媛媛，张红英

1.西南科技大学信息工程学院，四川绵阳 621010
2.西南科技大学特殊环境机器人技术四川省重点实验室，四川绵阳 621010

出版日期:2022-08-15 发布日期:2022-08-15

Single Exposure HDR Image Generation Method Based on Pix2pix Network Structure

ZHANG Yuanyuan, ZHANG Hongying

1.School of Information Engineering, Southwest University of Science and Technology, Mianyang, Sichuan 621010, China
2.Robot Technology Used for Special Environment Key Laboratory of Sichuan Province, Southwest University of Science and Technology, Mianyang, Sichuan 621010, China

Online:2022-08-15 Published:2022-08-15

摘要/Abstract

摘要： 针对单曝光高动态范围（high dynamic range，HDR）图像生成过程中图像欠曝光区域的细节恢复和图像色彩偏移的问题，提出一种基于pix2pix网络结构的单曝光HDR图像生成算法，采用pix2pix自编码网络结构，利用卷积步长代替池化层简化网络结构，在卷积过程中采用Leaky ReLU激活函数，有效地保留图像的细节信息，并使用绝对误差和余弦相似度函数构建损失函数，使网络能够对图像阴暗区域进行较好的扩展，保证图像色彩不发生偏移。实验结果证明，该算法能在有效地扩展图像阴暗区域的同时保证图像色彩不发生偏移。

关键词: 高动态成像, pix2pix网络, 余弦相似度, 图像色彩

Abstract: Aiming at the problem of detail recovery and color shift of underexposed area in single exposure HDR（high dynamic range） image generation, a single exposure HDR image generation algorithm based on pix2pix network structure is proposed. Pix2pix self coding network structure is adopted, convolution step is used to replace pooling layer to simplify network structure, and leaky network is used in convolution process, ReLU activation function can effectively retain the details of the image, and the absolute error and cosine similarity function are used to construct the loss function, so that the network can better expand the dark area of the image, and ensure that the image color does not shift. The experimental results show that the algorithm can effectively expand the dark area of the image while ensuring that the image color does not shift.

Key words: high dynamic imaging, pix2pix network, cosine similarity, image color

张媛媛, 张红英. 基于pix2pix网络结构的单曝光HDR图像生成方法[J]. 计算机工程与应用, 2022, 58(16): 242-248.

ZHANG Yuanyuan, ZHANG Hongying. Single Exposure HDR Image Generation Method Based on Pix2pix Network Structure[J]. Computer Engineering and Applications, 2022, 58(16): 242-248.

参考文献

[1] 单子健，郑科鹏，赵良福，等.HDR高动态范围图像技术及发展解读[J].广播电视信息，2018（4）：27-30.
SHAN Z J，ZHENG K P，ZHAO L F，et al.Interpretation of HDR high dynamic range image technology and development[J].Radio and Television Information，2018（4）：27-30.
[2] 白本督，刘卫华.高动态范围图像成像技术[J].西安邮电大学学报，2020，25（1）：63-67.
BAI B D，LIU W H.High dynamic range imaging technology[J].Journal of Xi’an University of Posts and Telecommunications，2020，25（1）：63-67.
[3] 霍永青，彭启琮.高动态范围图像及反色调映射算子[J].系统工程与电子技术，2012，34（4）：820-826.
HUO Y Q，PENG Q C.High dynamic range image and anti tone mapping operator[J].Systems Engineering and Electronic Technology，2012，34（4）：820-826.
[4] BANTERLE F，LEDDA P，DEBATTISTA K，et al.Inverse tone mapping[C]//Proceedings of the 4th International Conference on Computer Graphics and Interactive Techniques in Australasia and Southeast Asia.New York：ACM，2006：349-356.
[5] WANG T H，CHIU C W，WU W C，et al.Pseudo-multiple-exposure-based tone fusion with local region adjustment[J].IEEE Transactions on Multimedia，2015，17（4）：470-484.
[6] ZHANG J，LALONDE J F.Learning high dynamic range from outdoor panoramas[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision，2017：4519-4528.
[7] EILERTSEN G，KRONANDER J，DENES G，et al.HDR image reconstruction from a single exposure using deep CNNs[J].ACM Transactions on Graphics，2017，36（6）：1-15.
[8] ENDO Y，KANAMORI Y，MITANI J.Deep reverse tone mapping[J].ACM Transactions on Graphics，2017，36（6）：1-10.
[9] LEE S，AN G H，KANG S J.Deep chain HDRI：reconstructing a high dynamic range image from a single low dynamic range image[J].IEEE Access，2018，6：49913-49924.
[10] MARNERIDES D，BASHFORD-ROGERS T，HATCHETT J，et al.ExpandNet：a deep convolutional neural network for high dynamic range expansion from low dynamic range content[J].Computer Graphics Forum，2018，37（2）：37-49.
[11] ISOLA P，ZHU J Y，ZHOU T，et al.Image-to-image translation with conditional adversarial networks[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition，2017：1125-1134.
[12] FAIRCHILD M D.The HDR photographic survey[C]//Proceedings of the 15th Color and Imaging Conference，Society for Imaging Science and Technology，2007：233-238.
[13] KALANTARI N K，RAMAMOORTHI R.Deep high dynamic range imaging of dynamic scenes[J].ACM Transactions on Graphics，2017，36（4）：1-12.
[14] CAI J，GU S，ZHANG L.Learning a deep single image contrast enhancer from multi-exposure images[J].IEEE Transactions on Image Processing，2018，27（4）：2049-2062.
[15] TEO P C，HEEGER D J.Perceptual image distortion[C]//Proceedings of the 1st International Conference on Image Processing，1994，2：982-986.
[16] WANG Z，BOVIK A C，SHEIKH H R，et al.Image quality assessment：from error visibility to structural similarity[J].IEEE Transactions on Image Processing，2004，13（4）：600-612.
[17] MANTIUK R，KIM K J，REMPEL A G，et al.HDR-VDP-2：a calibrated visual metric for visibility and quality predictions in all luminance conditions[J].ACM Transactions on Graphics，2011，30（4）：1-14.

基于pix2pix网络结构的单曝光HDR图像生成方法

Single Exposure HDR Image Generation Method Based on Pix2pix Network Structure

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

编辑推荐

Metrics

[1]	魏玮，张芯月，朱叶. 改进的SIFT结合余弦相似度的人脸匹配算法[J]. 计算机工程与应用, 2020, 56(6): 207-212.
[2]	胡正平，王欣，孙德刚. 余弦权重逆稀疏框架视频目标跟踪算法[J]. 计算机工程与应用, 2019, 55(21): 206-213.
[3]	王昕宇，罗可. 具有全局记忆的LF蚁群聚类算法[J]. 计算机工程与应用, 2019, 55(20): 52-57.
[4]	周晓宇，张龙波，王雷，李鑫翔. 结合谱聚类与改进RSF模型的医学图像分割[J]. 计算机工程与应用, 2019, 55(15): 193-197.
[5]	尚玉玲1，曹建军2，李红梅1，刘艺1. 挖掘机构别名的Jaccard相似度数据空间转换方法[J]. 计算机工程与应用, 2018, 54(13): 88-92.
[6]	王彬宇1，刘文芬2，胡学先1，魏江宏1. 基于余弦距离选取初始簇中心的文本聚类研究[J]. 计算机工程与应用, 2018, 54(10): 11-18.
[7]	许钢，林园胜，江娟娟，江明. 改进型SIFT立体匹配算法研究[J]. 计算机工程与应用, 2015, 51(6): 134-138.