高级搜索

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于深度多级小波变换的图像盲去模糊算法

陈书贞 曹世鹏 崔美玥 练秋生

陈书贞, 曹世鹏, 崔美玥, 练秋生. 基于深度多级小波变换的图像盲去模糊算法[J]. 电子与信息学报, 2021, 43(1): 154-161. doi: 10.11999/JEIT190947
引用本文: 陈书贞, 曹世鹏, 崔美玥, 练秋生. 基于深度多级小波变换的图像盲去模糊算法[J]. 电子与信息学报, 2021, 43(1): 154-161. doi: 10.11999/JEIT190947
Shuzhen CHEN, Shipeng CAO, Meiyue CUI, Qiusheng LIAN. Image Blind Deblurring Algorithm Based on Deep Multi-level Wavelet Transform[J]. Journal of Electronics & Information Technology, 2021, 43(1): 154-161. doi: 10.11999/JEIT190947
Citation: Shuzhen CHEN, Shipeng CAO, Meiyue CUI, Qiusheng LIAN. Image Blind Deblurring Algorithm Based on Deep Multi-level Wavelet Transform[J]. Journal of Electronics & Information Technology, 2021, 43(1): 154-161. doi: 10.11999/JEIT190947

基于深度多级小波变换的图像盲去模糊算法

doi: 10.11999/JEIT190947
基金项目: 国家自然科学基金(61471313),河北省自然科学基金(F2019203318)
详细信息
    作者简介:

    陈书贞:女,1968年生,副教授,研究方向为图像处理、压缩感知、深度学习、相位恢复

    曹世鹏:男,1993年生,硕士生,研究方向为深度学习、动态场景去模糊

    崔美玥:女,1996年生,硕士生,研究方向为深度学习、人脸图像去模糊、超分辨率

    练秋生:男,1969年生,教授,博士生导师,研究方向为稀疏表示、深度学习、压缩感知及相位恢复

    通讯作者:

    练秋生 lianqs@ysu.edu.cn

  • 中图分类号: TN911.73

Image Blind Deblurring Algorithm Based on Deep Multi-level Wavelet Transform

Funds: The National Natural Science Foundation of China (61471313), The Natural Science Foundation of Hebei Province (F2019203318)
  • 摘要:

    近年来卷积神经网络广泛应用于单幅图像去模糊问题,卷积神经网络的感受野大小、网络深度等会影响图像去模糊算法性能。为了增大感受野以提高图像去模糊算法的性能,该文提出一种基于深度多级小波变换的图像盲去模糊算法。将小波变换嵌入编-解码结构中,在增大感受野的同时加强图像特征的稀疏性。为在小波域重构高质量图像,该文利用多尺度扩张稠密块提取图像的多尺度信息,同时引入特征融合块以自适应地融合编-解码之间的特征。此外,由于小波域和空间域对图像信息的表示存在差异,为融合这些不同的特征表示,该文利用空间域重建模块在空间域进一步提高重构图像的质量。实验结果表明该文方法在结构相似度(SSIM)和峰值信噪比(PSNR)上具有更好的性能,而且在真实模糊图像上具有更好的视觉效果。

  • 图  1  网络结构

    图  2  多尺度扩张稠密块

    图  3  特征融合块

    图  4  各个算法在GoPro测试集上的恢复结果对比

    图  5  文献[7]与本文算法在DVD数据集和真实数据集上的恢复结果对比

    表  1  各算法在GoPro测试数据集上的定量评估

    评价指标文献[2]文献[1]文献[5]文献[4]文献[6]文献[7]本文
    PSNR24.6425.1028.7029.0829.5530.2631.39
    SSIM0.8420.8900.9580.9140.9340.9340.952
    下载: 导出CSV

    表  2  各算法在GoPro测试数据集上的运行时间(s)

    评价指标文献[4]文献[6]文献[7]本文
    时间2.160.140.640.23
    下载: 导出CSV

    表  3  文献[7]与本文算法在DVD测试数据集上的定量评估

    评价指标文献[7]本文
    PSNR29.3429.97
    SSIM0.9140.921
    下载: 导出CSV

    表  4  各基准模型在GoPro测试集上的定量结果

    模型W-BW-C3W-MSW-FFW-SDR本文
    多尺度××××
    特征融合××××
    空间域图像重构××××
    嵌入卷积×××××
    PSNR30.9831.0231.1031.0931.1331.39
    SSIM0.9490.9490.9500.9500.9500.952
    下载: 导出CSV

    表  5  两种训练方法在GoPro测试集上的定量对比

    训练方法整体训练模块化训练
    PSNR31.0531.39
    SSIM0.9490.952
    下载: 导出CSV
  • XU Li, ZHENG Shicheng, and JIA Jiaya. Unnatural l0 sparse representation for natural image deblurring[C]. 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, USA, 2013: 1107–1114. doi: 10.1109/CVPR.2013.147.
    SUN Jian, CAO Wenfei, XU Zongben, et al. Learning a convolutional neural network for non-uniform motion blur removal[C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015: 769–777. doi: 10.1109/CVPR.2015.7298677.
    GONG Dong, YANG Jie, LIU Lingqiao, et al. From motion blur to motion flow: A deep learning solution for removing heterogeneous motion blur[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017: 3806–3815. doi: 10.1109/CVPR.2017.405.
    NAH S, KIM T H, and LEE K M. Deep multi-scale convolutional neural network for dynamic scene deblurring[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 257–265. doi: 10.1109/CVPR.2017.35.
    KUPYN O, BUDZAN V, MYKHAILYCH M, et al. DeblurGAN: Blind motion deblurring using conditional adversarial networks[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 8183–8192. doi: 10.1109/CVPR.2018.00854.
    KUPYN O, MARTYNIUK T, WU Junru, et al. DeblurGAN-v2: Deblurring (orders-of-magnitude) faster and better[C]. 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Korea (South), 2019: 8877–8886. doi: 10.1109/ICCV.2019.00897.
    TAO Xin, GAO Hongyun, SHEN Xiaoyong, et al. Scale-recurrent network for deep image deblurring[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 8174–8182. doi: 10.1109/CVPR.2018.00853.
    梁晓萍, 郭振军, 朱昌洪. 基于头脑风暴优化算法的BP神经网络模糊图像复原[J]. 电子与信息学报, 2019, 41(12): 2980–2986. doi: 10.11999/JEIT190261

    LIANG Xiaoping, GUO Zhenjun, and ZHU Changhong. BP neural network fuzzy image restoration based on brain storming optimization algorithm[J]. Journal of Electronics &Information Technology, 2019, 41(12): 2980–2986. doi: 10.11999/JEIT190261
    RONNEBERGER O, FISCHER P, and BROX T. U-net: Convolutional networks for biomedical image segmentation[C]. The 18th International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 2015: 234–241. doi: 10.1007/978-3-319-24574-4_28.
    CHEN Dongdong, HE Mingming, FAN Qingnan, et al. Gated context aggregation network for image dehazing and deraining[C]. 2019 IEEE Winter Conference on Applications of Computer Vision, Waikoloa Village, USA, 2019: 1375–1383. doi: 10.1109/WACV.2019.00151.
    LIU Pengju, ZHANG Hongzhi, ZHANG Kai, et al. Multi-level wavelet-CNN for image restoration[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, USA, 2018: 886–895. doi: 10.1109/CVPRW.2018.00121.
    JIN Meiguang, HIRSCH M, and FAVARO P. Learning face deblurring fast and wide[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, USA, 2018: 858–866. doi: 10.1109/CVPRW.2018.00118.
    GUO Tiantong, MOUSAVI H S, VU T H, et al. Deep wavelet prediction for image super-resolution[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, USA, 2017: 1100–1109. doi: 10.1109/CVPRW.2017.148.
    LI Xiang, WANG Wenhai, HU Xiaolin, et al. Selective kernel networks[C]. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019: 510–519. doi: 10.1109/CVPR.2019.00060.
    HUANG Gao, LIU Zhuang, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 2261–2269. doi: 10.1109/CVPR.2017.243.
    陈书贞, 张祎俊, 练秋生. 基于多尺度稠密残差网络的JPEG压缩伪迹去除方法[J]. 电子与信息学报, 2019, 41(10): 2479–2486. doi: 10.11999/JEIT180963

    CHEN Shuzhen, ZHANG Yijun, and LIAN Qiusheng. JPEG compression artifacts reduction algorithm based on multi-scale dense residual network[J]. Journal of Electronics &Information Technology, 2019, 41(10): 2479–2486. doi: 10.11999/JEIT180963
    WOO S, PARK J, LEE J Y, et al. CBAM: Convolutional block attention module[C]. The 15th European Conference on Computer Vision, Munich, Germany, 2018: 3–19. doi: 10.1007/978-3-030-01234-2_1.
    SU Shuochen, DELBRACIO M, WANG Jue, et al. Deep video deblurring for hand-held cameras[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 237–246. doi: 10.1109/CVPR.2017.33.
    HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 770–778. doi: 10.1109/CVPR.2016.90.
    LAI Weisheng, HUANG Jiabin, HU Zhe, et al. A comparative study for single image blind deblurring[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 1701–1709. doi: 10.1109/CVPR.2016.188.
  • 加载中
图(5) / 表(5)
计量
  • 文章访问数:  1276
  • HTML全文浏览量:  1010
  • PDF下载量:  230
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-11-27
  • 修回日期:  2020-10-29
  • 网络出版日期:  2020-11-25
  • 刊出日期:  2021-01-15

目录

    /

    返回文章
    返回