1.福州大学 先进制造学院, 福建 泉州 362000
2.中国科学院 福建物质结构研究所, 福建 福州 350108
3.中国科学院 海西研究院 泉州装备制造研究中心, 福建 泉州 362000
[ "杜均森(1997—),男,广东湛江人,硕士研究生,2020年于福州大学获得学士学位,主要从事稀疏编码及图像生成领域的研究。E-mail:735493942@qq.com" ]
[ "郭杰龙(1988—),男,福建泉州人,硕士,工程师,2015年于中南民族大学获得硕士学位,主要从事机器视觉、图像处理方面的研究。E-mail:gjl@fjirsm.ac.cn" ]
扫 描 看 全 文
杜均森, 郭杰龙, 俞辉, 等. 基于卷积稀疏编码与生成对抗网络的图像超分辨率重建[J]. 液晶与显示, 2023,38(10):1423-1433.
DU Jun-sen, GUO Jie-long, YU Hui, et al. Super-resolution image reconstruction based on convolutional sparse coding and generative adversarial networks[J]. Chinese Journal of Liquid Crystals and Displays, 2023,38(10):1423-1433.
杜均森, 郭杰龙, 俞辉, 等. 基于卷积稀疏编码与生成对抗网络的图像超分辨率重建[J]. 液晶与显示, 2023,38(10):1423-1433. DOI: 10.37188/CJLCD.2022-0406.
DU Jun-sen, GUO Jie-long, YU Hui, et al. Super-resolution image reconstruction based on convolutional sparse coding and generative adversarial networks[J]. Chinese Journal of Liquid Crystals and Displays, 2023,38(10):1423-1433. DOI: 10.37188/CJLCD.2022-0406.
针对现有图像超分辨率重建算法的重建图像仍存在高频信息缺失、噪点增多问题,本文提出了一种基于卷积稀疏编码与生成对抗网络的图像超分辨率重建模型。首先,利用卷积网络实现稀疏编码并获取图像稀疏表示,充分利用图像的先验信息,有效避免重建图像高频信息缺失和噪点增多的问题;在得到低分辨率图像的稀疏表示后,通过重建模块对稀疏表示进行重建得到超分辨率图像;随后,鉴别器对重建图像进行鉴别,缓解由PSNR主导的算法导致重建图像趋于平滑的问题。在不断对抗训练后,最后的重建图像具有更好的视觉效果。本文在Set5、Set14、BSD100和Urban100通用测试数据集上进行2倍和4倍的超分辨率重建实验,并与Bicubic、SRGAN、EDSR和ESRGAN对比。与ESRGAN方法相比,本文模型在4个数据集上平均PSNR提升约0.702 8 dB,平均SSIM提升约0.047,平均LPIPS提升了0.016。实验结果表明,所提出的模型具有较强的竞争力,能够恢复更多的细纹理细节且具有更好的清晰度。
To address the problems of high-frequency information missing and increased noise in images generated by existing image super-resolution reconstruction algorithms, this paper proposes an image super-resolution reconstruction model based on convolutional sparse coding and generative adversarial networks. Firstly, convolutional networks are employed to implement sparse coding and obtain a sparse representation of the image, which makes full use of the prior information of the image and effectively avoids the problems of high-frequency information missing and increased noise in the reconstructed image. After obtaining the sparse representation of the low-resolution image, the sparse representation is reconstructed by the reconstruction module to obtain the super-resolution image. Subsequently, the discriminator discriminates the reconstructed image to alleviate the problem that the reconstructed image tends to be smooth due to the PSNR-dominated algorithm. After continuous adversarial training, the final generated super-resolution images are made to have better visual effects. The super-resolution reconstruction experiments are performed on Set5, Set14, BSD100 and Urban100 general test datasets at 2× and 4× and compared with Bicubic, SRGAN, EDSR and ESRGAN methods. Compared with ESRGAN, the average PSNR improvement is about 0.702 8 dB, the average SSIM improvement is about 0.047, and the average LPIPS improvement is 0.016 on the four datasets.Experimental results show that the proposed model is highly competitive and enables the recovery of more fine-texture details with better definition.
图像处理图像超分辨率稀疏表示生成对抗网络
image processingimage super resolutionsparse representationgenerative adversarial network
何鹏浩,余映,徐超越.基于动态金字塔和子空间注意力的图像超分辨率重建网络[J].计算机科学,2022,49(S2):210900202. doi: 10.11896/jsjkx.210900202http://dx.doi.org/10.11896/jsjkx.210900202
HE P H, YU Y, XU C Y. Image super-resolution reconstruction network based on dynamic pyramid and subspace attention [J]. Computer Science, 2022, 49(S2): 210900202. (in Chinese). doi: 10.11896/jsjkx.210900202http://dx.doi.org/10.11896/jsjkx.210900202
PARK S C, PARK M K, KANG M G. Super-resolution image reconstruction: a technical overview [J]. IEEE Signal Processing Magazine, 2003, 20(3): 21-36. doi: 10.1109/msp.2003.1203207http://dx.doi.org/10.1109/msp.2003.1203207
HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks [J]. Science, 2006, 313(5786): 504-508. doi: 10.1126/science.1127647http://dx.doi.org/10.1126/science.1127647
HOU H, ANDREWS H. Cubic splines for image interpolation and digital filtering [J]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1978, 26(6): 508-517. doi: 10.1109/tassp.1978.1163154http://dx.doi.org/10.1109/tassp.1978.1163154
KEYS R. Cubic convolution interpolation for digital image processing [J]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1981, 29(6): 1153-1160. doi: 10.1109/tassp.1981.1163711http://dx.doi.org/10.1109/tassp.1981.1163711
BABACAN S D, MOLINA R, KATSAGGELOS A K. Parameter estimation in TV image restoration using variational distribution approximation [J]. IEEE Transactions on Image Processing, 2008, 17(3): 326-339. doi: 10.1109/tip.2007.916051http://dx.doi.org/10.1109/tip.2007.916051
PATTI A J, SEZAN M I, TEKALP A M. Robust methods for high-quality stills from interlaced video in the presence of dominant motion [J]. IEEE Transactions on Circuits and Systems for Video Technology, 1997, 7(2): 328-342. doi: 10.1109/76.564111http://dx.doi.org/10.1109/76.564111
IRANI M, PELEG S. Improving resolution by image registration [J]. CVGIP: Graphical Models and Image Processing, 1991, 53(3): 231-239. doi: 10.1016/1049-9652(91)90045-lhttp://dx.doi.org/10.1016/1049-9652(91)90045-l
林国军,蒋行国,杨明中,等.基于叠加协同表示分类的人脸识别[J].液晶与显示,2020,35(2):161-166. doi: 10.3788/yjyxs20203502.0161http://dx.doi.org/10.3788/yjyxs20203502.0161
LIN G J, JIANG X G, YANG M Z, et al. Face recognition based on superposed collaborative representation based classification [J]. Chinese Journal of Liquid Crystals and Displays, 2020, 35(2): 161-166. (in Chinese). doi: 10.3788/yjyxs20203502.0161http://dx.doi.org/10.3788/yjyxs20203502.0161
HE L, QI H, ZARETZKI R. Beta process joint dictionary learning for coupled feature spaces with application to single image super-resolution [C]// Proceedings of the IEEE conference on computer vision and pattern recognition. Portland, Oregon:IEEE , 2013: 345-352. doi: 10.1109/cvpr.2013.51http://dx.doi.org/10.1109/cvpr.2013.51
谢斌,黄安,黄辉.本征图像分解的稀疏表示彩色图像去噪算法[J].液晶与显示,2019,34(11):1104-1114. doi: 10.3788/yjyxs20193411.1104http://dx.doi.org/10.3788/yjyxs20193411.1104
XIE B, HUANG A, HUANG H. Colorimage denoising algorithm based on intrinsic image decomposition and sparse representation [J]. Chinese Journal of Liquid Crystals and Displays, 2019, 34(11): 1104-1114. (in Chinese). doi: 10.3788/yjyxs20193411.1104http://dx.doi.org/10.3788/yjyxs20193411.1104
YANG J C, WRIGHT J, HUANG T S, et al. Image super-resolution via sparse representation [J]. IEEE Transactions on Image Processing, 2010, 19(11): 2861-2873. doi: 10.1109/tip.2010.2050625http://dx.doi.org/10.1109/tip.2010.2050625
ZEYDE R, ELAD M, PROTTER M. On single image scale-up using sparse-representations [C]. 7th International Conference on Curves and Surfaces. Avignon: Springer, 2012: 711-730. doi: 10.1007/978-3-642-27413-8_47http://dx.doi.org/10.1007/978-3-642-27413-8_47
LUO Y, ZHAO Y F, LI J X, et al. Computational imaging without a computer: seeing through random diffusers at the speed of light [J]. eLight, 2022, 2(1): 4. doi: 10.1186/s43593-022-00012-4http://dx.doi.org/10.1186/s43593-022-00012-4
ZUO C, QIAN J M, FENG S J, et al. Deep learning in optical metrology: a review [J]. Light: Science & Applications, 2022, 11(1): 39. doi: 10.1038/s41377-022-00714-xhttp://dx.doi.org/10.1038/s41377-022-00714-x
SITU G. Deep holography [J]. Light: Advanced Manufacturing, 2022, 3(2): 8. doi: 10.37188/lam.2022.013http://dx.doi.org/10.37188/lam.2022.013
DONG C, LOY C C, HE K M, et al. Image super-resolution using deep convolutional networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2): 295-307. doi: 10.1109/tpami.2015.2439281http://dx.doi.org/10.1109/tpami.2015.2439281
KIM J, LEE J K, LEE K M. Accurate image super-resolution using very deep convolutional networks [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 1646-1654. doi: 10.1109/cvpr.2016.182http://dx.doi.org/10.1109/cvpr.2016.182
SHI W Z, CABALLERO J, HUSZÁR F, et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 1874-1883. doi: 10.1109/cvpr.2016.207http://dx.doi.org/10.1109/cvpr.2016.207
黄友文,唐欣,周斌.结合双注意力和结构相似度量的图像超分辨率重建网络[J].液晶与显示,2022,37(3):367-375. doi: 10.37188/CJLCD.2021-0178http://dx.doi.org/10.37188/CJLCD.2021-0178
HUANG Y W, TANG X, ZHOU B. Image super-resolution reconstruction network with dual attention and structural similarity measure [J]. Chinese Journal of Liquid Crystals and Displays, 2022, 37(3): 367-375. (in Chinese). doi: 10.37188/CJLCD.2021-0178http://dx.doi.org/10.37188/CJLCD.2021-0178
赵圆圆,施圣贤.融合多尺度特征的光场图像超分辨率方法[J].光电工程,2020,47(12):200007.
ZHAO Y Y, SHI S X. Light-field image super-resolution based on multi-scale feature fusion [J]. Opto-Electronic Engineering, 2020, 47(12): 200007. (in Chinese)
GREGOR K, LECUN Y. Learning fast approximations of sparse coding [C]//Proceedings of the 27th International Conference on International Conference on Machine Learning. Haifa: ACM, 2010: 399-406.
DAUBECHIES I, DEFRISE M, DE MOL C. An iterative thresholding algorithm for linear inverse problems with a sparsity constraint [J]. Communications on Pure and Applied Mathematics, 2004, 57(11): 1413-1457. doi: 10.1002/cpa.20042http://dx.doi.org/10.1002/cpa.20042
LIU D, WANG Z W, WEN B H, et al. Robust single image super-resolution via deep networks with sparse prior [J]. IEEE Transactions on Image Processing, 2016, 25(7): 3194-3207. doi: 10.1109/tip.2016.2564643http://dx.doi.org/10.1109/tip.2016.2564643
SRETER H, GIRYES R. Learned convolutional sparse coding [C]. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Calgary: IEEE, 2018: 2191-2195. doi: 10.1109/icassp.2018.8462313http://dx.doi.org/10.1109/icassp.2018.8462313
CRESWELL A, WHITE T, DUMOULIN V, et al. Generative adversarial networks: an overview [J]. IEEE Signal Processing Magazine, 2018, 35(1): 53-65. doi: 10.1109/msp.2017.2765202http://dx.doi.org/10.1109/msp.2017.2765202
LEDIG C, THEIS L, HUSZÁR F, et al. Photo-realistic single image super-resolution using a generative adversarial network [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 105-114. doi: 10.1109/cvpr.2017.19http://dx.doi.org/10.1109/cvpr.2017.19
WANG X T, YU K, WU S X, et al. ESRGAN: enhanced super-resolution generative adversarial networks [C]//Proceedings of the European Conference on Computer Vision. Munich: Springer, 2019: 63-79. doi: 10.1007/978-3-030-11021-5_5http://dx.doi.org/10.1007/978-3-030-11021-5_5
TOŠIĆ I, FROSSARD P. Dictionary learning [J]. IEEE Signal Processing Magazine, 2011, 28(2): 27-38. doi: 10.1109/msp.2010.939537http://dx.doi.org/10.1109/msp.2010.939537
CAI T T, WANG L. Orthogonal matching pursuit for sparse signal recovery [J]. IEEE Transactions on Information Theory, 2011, 57(7): 4680-4688. doi: 10.1109/tit.2011.2146090http://dx.doi.org/10.1109/tit.2011.2146090
AHARON M, ELAD M, BRUCKSTEIN A. K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation [J]. IEEE Transactions on Signal Processing, 2006, 54(11): 4311-4322. doi: 10.1109/tsp.2006.881199http://dx.doi.org/10.1109/tsp.2006.881199
SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition [C]. 3rd International Conference on Learning Representations (ICLR). San Diego: ICLR, 2015: 1-14.
ZHANG R, ISOLA P, EFROS A A, et al. The unreasonable effectiveness of deep features as a perceptual metric [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 586-595. doi: 10.1109/cvpr.2018.00068http://dx.doi.org/10.1109/cvpr.2018.00068
0
浏览量
66
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构