基于算法展开的图像盲去模糊深度学习网络

doi:10.6040/j.issn.1672-3961.0.2022.298

摘要/Abstract

摘要： 针对图像盲去模糊问题,基于变分模型的迭代优化展开形式设计了相应的变分深度学习网络,有效克服了传统变分方法计算效率低和深度学习方法可解释性差的问题。设计网络包含2部分: 利用算法展开策略实现基于L₀正则化估计模糊核的子网络;基于估计的模糊核及图像恢复正则化模型的非盲去卷积子网络,该子网络充分利用了双通道的编解码网络结构。为确保模糊核估计的准确性和图像内容的一致性,损失函数由均方误差损失和结构相似性损失构成。L₀正则化的使用有助于快速准确地完成模糊核估计;图像恢复正则化模型的使用有助于边缘和图像细节的保持。在Levin数据集上的试验结果表明,所提算法在峰值信噪比上较目前先进算法至少提高了2.14 dB。

关键词: 图像去模糊, 算法展开, 正则化方法, 模糊核估计, 深度学习

中图分类号:

TP391

王旭晴,魏伟波,杨光宇,宋金涛,吕婷,潘振宽. 基于算法展开的图像盲去模糊深度学习网络[J]. 山东大学学报 (工学版), 2023, 53(6): 35-46.

WANG Xuqing, WEI Weibo, YANG Guangyu, SONG Jintao, LÜ Ting, PAN Zhenkuan. Blind image deblurring deep learning network based on algorithm unrolling[J]. Journal of Shandong University(Engineering Science), 2023, 53(6): 35-46.

参考文献

[1] CHO S, LEE S. Fast motion deblurring[J]. ACM Transactions on Graphics, 2009, 28(5): 1-8.
[2] PAN J, SU Z. Fast l0-regularized kernel estimation for robust motion deblurring[J]. IEEE Signal Processing Letters, 2013, 20(9): 841-844.
[3] PAN J, HU Z, SU Z, et al. L0-regularized intensity and gradient prior for deblurring text images and beyond[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(2): 342-355.
[4] 唐梦, 彭国华, 郑红婵. 基于正则化方法的图像盲去模糊[J]. 计算机应用研究, 2014, 31(2): 596-599. TANG Meng, PENG Guohua, ZHENG Hongchan. Blind image deblurring based on regularization method[J]. Application Research of Computers, 2014, 31(2): 596-599.
[5] PAN J, SUN D, PFISTER H, et al. Deblurring images via dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(10): 2315-2328.
[6] CHAKRABARTI A. A neural approach to blind motion deblurring[C] //Proceedings of Computer Vision — ECCV 2016. Amsterdam, Netherlands: Springer, 2016: 221-235.
[7] XU X, PAN J, ZHANG Y J, et al. Motion blur kernel estimation via deep learning[J]. IEEE Transactions on Image Processing, 2018, 27(1): 194-205.
[8] SCHULER C J, HIRSCH M, HARMELING S, et al. Learning to deblur[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(7): 1439-1451.
[9] LIU K H, YEH C H, CHUNG J W, et al. A motion deblur method based on multi-scale high frequency residual image learning[J]. IEEE, 2020, 8: 66025-66036.
[10] NAN Y, JI H. Deep learning for handling kernel/model uncertainty in image deconvolution[C] //Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Seattle, USA: IEEE, 2020: 2385-2394.
[11] TAO X, GAO H, SHEN X, et al. Scale-recurrent network for deep image deblurring[C] //Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Salt Lake City, USA: IEEE, 2018: 8174-8182.
[12] KUPYN O, BUDZAN V, MYKHAILYCH M, et al. DeblurGAN: blind motion deblurring using conditional adversarial networks[C] //Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Salt Lake City, USA: IEEE, 2018: 8183-8192.
[13] MONGA V, LI Y, ELDAR Y C. Algorithm unrolling: interpretable, efficient deep learning for signal and image processing[J]. IEEE Signal Processing Magazine, 2021, 38(2): 18-44.
[14] ZHANG J, GHANEM B. ISTA-Net: interpretable optimization-inspired deep network for image compressive sensing[C] //Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Salt Lake City, USA: IEEE, 2018: 1828-1837.
[15] LI Y, TOFIGHI M, GENG J, et al. Efficient and interpretable deep blind image deblurring via algorithm unrolling[J]. IEEE Transactions on Computational Imaging, 2020, 6: 666-681.
[16] WANG Y, YANG J, YIN W, et al. A new alternating minimization algorithm for total variation image reconstruction[J]. SIAM Journal on Imaging Sciences, 2008, 1(3): 248-272.
[17] XIN B, WANG Y, GAO W, et al. Maximal sparsity with deep networks[C] //Proceedings of the 30th International Conference on Neural Information Processing Systems(NIPS16). Red Hook, USA: Curran Associates Inc, 2016: 4347-4355.
[18] WANG Z, LING Q, HUANG T S. Learning deep l0 encoders[C] //Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence(AAAI16). Phoenix, USA: AAAI, 2016: 2194-2200.
[19] MARTIN D, FOWLKES C, TAL D, et al. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics[C] //Proceedings of Eighth IEEE International Conference on Computer Vision(ICCV 2001). Vancouver, Canada, 2001: 416-423.
[20] LEVIN A, WEISS Y, DURAND F, et al. Understanding and evaluating blind deconvolution algorithms[C] //Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Miami, USA: IEEE, 2009: 1964-1971.
[21] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft coco: common objects in context[C] //Proceedings of Computer Vision — ECCV 2014. Zurich, Switzerland: Springer, 2014: 740-755.
[22] SUN L, CHO S, WANG J, et al. Edge-based blur kernel estimation using patch priors[C] //Proceedings of IEEE International Conference on Computational Photography(ICCP). Cambridge, USA: IEEE, 2013: 1-8.
[23] NAH S, KIM T H, LEE K M. Deep multi-scale convolutional neural network for dynamic scene deblurring[C] //Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Honolulu, USA: IEEE, 2017: 257-265.
[24] HU Z, YANG M H. Good regions to deblur[C] //Proceedings of Computer Vision—ECCV 2012. Florence, Italy: Springer Berlin Heidelberg, 2012: 59-72.

相关文章 15

[1]	李家春,李博文,常建波. 一种高效且轻量的RGB单帧人脸反欺诈模型[J]. 山东大学学报 (工学版), 2023, 53(6): 1-7.
[2]	王碧瑶,韩毅,崔航滨,刘毅超,任铭然,高维勇,陈姝廷,刘嘉巍,崔洋. 基于图像的道路语义分割检测方法[J]. 山东大学学报 (工学版), 2023, 53(5): 37-47.
[3]	周晓昕,廖祝华,刘毅志,赵肄江,方艺洁. 融合历史与当前交通流量的信号控制方法[J]. 山东大学学报 (工学版), 2023, 53(4): 48-55.
[4]	于畅,伍星,邓秋菊. 基于深度学习的多视角螺钉缺失智能检测算法[J]. 山东大学学报 (工学版), 2023, 53(4): 104-112.
[5]	宋佳芮,陈艳平,王凯,黄瑞章,秦永彬. 基于Affix-Attention的命名实体识别语义补充方法[J]. 山东大学学报 (工学版), 2023, 53(2): 70-76.
[6]	袁钺,王艳丽,刘勘. 基于空洞卷积块架构的命名实体识别模型[J]. 山东大学学报 (工学版), 2022, 52(6): 105-114.
[7]	李旭涛,杨寒玉,卢业飞,张玮. 基于深度学习的遥感图像道路分割[J]. 山东大学学报 (工学版), 2022, 52(6): 139-145.
[8]	孟令灿,聂秀山,张雪. 基于遮挡目标去除的公交车拥挤度分类算法[J]. 山东大学学报 (工学版), 2022, 52(4): 83-88.
[9]	杨霄,袭肖明,李维翠,杨璐. 基于层次化双重注意力网络的乳腺多模态图像分类[J]. 山东大学学报 (工学版), 2022, 52(3): 34-41.
[10]	王心哲,邓棋文,王际潮,范剑超. 深度语义分割MRF模型的海洋筏式养殖信息提取[J]. 山东大学学报 (工学版), 2022, 52(2): 89-98.
[11]	蒋桐雨, 陈帆, 和红杰. 基于非对称U型金字塔重建的轻量级人脸超分辨率网络[J]. 山东大学学报 (工学版), 2022, 52(1): 1-8.
[12]	吴建清,宋修广. 同步定位与建图技术发展综述[J]. 山东大学学报 (工学版), 2021, 51(5): 16-31.
[13]	柴庆发,孙守晶,邱吉福,陈明,魏振,丛伟. 气象灾害条件下电网应急物资预测方法[J]. 山东大学学报 (工学版), 2021, 51(3): 76-83.
[14]	杨修远,彭韬,杨亮,林鸿飞. 基于知识蒸馏的自适应多领域情感分析[J]. 山东大学学报 (工学版), 2021, 51(3): 15-21.
[15]	廖锦萍,莫毓昌,YAN Ke. 基于C-LSTM的短期用电预测模型和应用[J]. 山东大学学报 (工学版), 2021, 51(2): 90-97.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed