浏览全部资源
扫码关注微信
Received：24 November 2021，
Revised：2022-5-7，
Accepted：14 May 2022，
Published：16 September 2022
移动端阅览
Bayer阵列图像去马赛克技术是对稀疏采样的Bayer阵列图像进行RGB信息重建，图像重建质量是成像设备评价的重要因素之一，同时也对其他计算机视觉任务(如图像分割、人脸识别)产生影响。随着深度学习方法的快速发展，图像去马赛克领域提出了多种高性能算法。为了便于研究者更全面了解图像去马赛克算法的原理和研究进展，本文对该领域的经典算法和深度学习算法进行综述。首先对Bayer采样阵列原理和图像去马赛克技术进行概述。然后将现有方法分为传统方法和基于深度学习方法两类进行总结，同时根据去马赛克任务是否具有独立性，将深度学习方法分为独立去马赛克任务和联合去马赛克任务两类，分析不同方法的原理和优缺点，重点阐述基于深度学习的去马赛克方法的网络结构和重建机理，介绍去马赛克领域常用的公共数据集和性能评价指标，并对图像去马赛克相关实验进行分析对比。最后，围绕网络深度、运算效率和实用性等方面分析了现阶段图像去马赛克技术面临的挑战及未来发展方向。目前，基于深度学习的图像去马赛克方法已成为主流发展方向，但仍然存在计算成本较高、实际应用性不强等问题。因此，如何开发出重建精度高、处理时间短以及实用性强的图像去马赛克方法，是该领域未来重要的研究方向。
The Bayer array image demosaicing technology is one of the essential parts in the digital image signal processing process mechanism
which reconstructs the sparsely sampled Bayer array image into a completed RGB image. In terms of a single-sensor image acquisition of Bayer color filter array
single color channel value is just recorded by the position of each pixel. The other two color channels information needs to be reconstructed by the Bayer color filter array demosaicking technology. The reconstruction effect of qualified RGB information determines the accuracy of computer vision analysis like image segmentation and face recognition. Deep learning based Bayer array image demosaicing technology has promoted more high-performance algorithms nowadays. To recognize the principle and development of image demosaicing algorithms
we review some classic algorithms and analyze the key concepts. First
an overview is illustrated for the Bayer sampling array and image demosaicing technology. Next
we divide the existing methods into two categories in accordance with traditional methods and deep learning methods. The pros and cons of different methods are analyzed and the information transmission issue of the learning-based demosaicing network is focused on. We introduce traditional demosaicing methods in brief based on the basic principle
growth path and applications of the residual interpolation algorithms. Specifically
we divide the learning-based methods into single demosaic algorithms and joint multi-task demosaic algorithms derived of the independence of the demosaicing task. Single demosaicing algorithms can be divided into three categories of those are two-stage demosaicing network
three-stage demosaicing network
and end-to-end demosaicing network. Joint multi-task demosaic algorithms are mostly based on end-to-end multiple networks structure like full convolution
residual
densely connected
U-Net
feature pyramid
and generative adversarial network (GAN). At the same time
we compare seven representative methods to the two benched datasets of Kodak and McMaster
including three traditional methods and four deep learning methods. In addition
we introduce common public datasets and performance evaluation metrics peak signal-to-noise ratio (PSNR) and structural similarity in the field of demosaicing. Finally
we analyze the technical problems faced by the current image demosaicing technology and the future development direction from the perspectives of its network depth
computing efficiency
and feasibility. Our experimental results show that the deep learning based method surpasses the traditional methods in terms of objective quality evaluation indicators and subjective vision. We clarified that the highest PSNR value of the learning-based methods on the Kodak dataset surpassed the traditional methods by 12.73 dB
and the highest PSNR value of the learning-based methods on the McMaster dataset surpassed the traditional methods by 5.10 dB. The traditional method obtains the estimated value of the color image via the degradation model of the Bayer array image and some prior information. However
some distortion issues appear in the clear edges and multi-textured areas of the reconstructed image
such as color artifacts and checkerboard effects. Current deep learning methods have become the main development prospects in the field of demosaicing. Although the reconstructed image of learning-based methods is more similar to the original image than the traditional method on the visual effect and accuracy
it also has the problem of high computational cost and poor practical applicability. It is challenged to guarantee the accuracy of network algorithms and reduce the computational cost of the network both. Therefore
a high-performance and effective image demosaicing method has to be developed further in terms of datasets option
network structure optimization
and improvement of computing efficiency.
Adams J E Jr. 1995. Interactions between color plane interpolation and other image processing functions in electronic photography//Proceedings Cameras and Systems for Electronic Photography and Scientific Imaging. San Jose, USA: SPIE: 144-151 [ DOI: 10.1117/12.204825 http://dx.doi.org/10.1117/12.204825 ]
Bayer B E. 1976. Color imaging array. U.S., No. 3 971 065
Cui K, Jin Z and Steinbach E. 2018. Color image demosaicking using a 3-stage convolutional neural network structure//Proceedings of the 25th IEEE International Conference on Image Processing. Athens, Greece: IEEE: 2177-2181 [ DOI: 10.1109/ICIP.2018.8451020 http://dx.doi.org/10.1109/ICIP.2018.8451020 ]
Din S, Paul A and Ahmad A. 2020. Lightweight deep dense demosaicking and denoising using convolutional neural networks. Multimedia Tools and Applications, 79(45): 34385-34405 [DOI: 10.1007/s11042-020-08908-4]
Dong C, Loy C C, He K M and Tang X O. 2014. Learning a deep convolutional network for image super-resolution//Proceedings of the 13th European Conference on Computer Vision. Zurich, Switzerland: Springer: 184-199 [ DOI: 10.1007/978-3-319-10593-2_13 http://dx.doi.org/10.1007/978-3-319-10593-2_13 ]
Dong W S, Yuan M R, Li X and Shi GM. 2018. Joint demosaicing and denoising with perceptual optimization on a generative adversarial network [EB/OL ] . [2021-10-29 ] . https://arxiv.org/pdf/1802.04723v1.pdf https://arxiv.org/pdf/1802.04723v1.pdf
Gharbi M, Chaurasia G, Paris S and Durand F. 2016. Deep joint demosaicking and denoising. ACM Transactions on Graphics, 35(6): #191 [DOI: 10.1145/2980179.2982399]
Goodfellow I J, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A and Bengio Y. 2014. Generative adversarial nets [EB/OL ] . [2021-10-29 ] . https://arxiv.org/pdf/1406.2661.pdf https://arxiv.org/pdf/1406.2661.pdf
Guo Y, Jin Q Y, Facciolo G, Zeng T Y and Morel J M. 2020. Residual learning for e ffective joint demosaicing-denoising [EB/OL ] . [2021-10-29 ] . https://arxiv.org/pdf/2009.06205.pdf https://arxiv.org/pdf/2009.06205.pdf
He K M, Sun J and Tang X O. 2013. Guided image filtering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(6): 1397-1409 [DOI: 10.1109/TPAMI.2012.213]
He K M, Zhang X Y, Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE: 770-778 [ DOI: 10.1109/CVPR.2016.90 http://dx.doi.org/10.1109/CVPR.2016.90 ]
Hou H and Andrews H. 1978. Cubic splines for image interpolation and digital filtering. IEEE Transactions on Acoustics, Speech, and Signal Processing, 26(6): 508-517 [DOI: 10.1109/TASSP.1978.1163154]
Huang G, Liu Z, van der Maaten L and Weinberger K Q. 2017. Densely connected convolutional networks//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE: 2261-2269 [ DOI: 10.1109/CVPR.2017.243 http://dx.doi.org/10.1109/CVPR.2017.243 ]
Huang T, Wu F F, Dong W S, Shi G M and Li X. 2018. Lightweight deep residue learning for joint color image demosaicking and denoising//Proceedings of the 24th International Conference on Pattern Recognition. Beijing, China: IEEE: 127-132 [ DOI: 10.1109/ICPR.2018.8546057 http://dx.doi.org/10.1109/ICPR.2018.8546057 ]
Ioffe S and Szegedy C. 2015. Batch normalization: accelerating deep network training by reducing internal covariate shift//Proceedings of the 32nd International Conference on Machine Learning. Lille, France: JMLR. org: 448-456
Iriyama T, Sato M, Aomori H and Otake T. 2021. Deep demosaicking considering inter-channel correlation and self-similarity. Nonlinear Theory and Its Applications, 12(3): 453-463 [DOI: 10.1587/nolta.12.453]
Jia F, Ma L Y, Yang Y J and Zeng T Y. 2021. Pixel-Attention CNN with color correlation loss for color image denoising. IEEE Signal Processing Letters, 28: 1600-1604 [DOI: 10.1109/LSP.2021.3100263]
Kang M and Jung M. 2020. Low-dimensional manifold model for demosaicking from a RGBW color filter array. Signal, Image and Video Processing, 14(1): 143-150 [DOI: 10.1007/s11760-019-01535-z]
Kang Q, Fu Y and Huang H. 2019. Deep color image demosaicking with feature pyramid ch annel attention//Proceedings of 2019 IEEE International Conference on Multimedia and Expo Workshops. Shanghai, China: IEEE: 246-251 [ DOI: 10.1109/ICMEW.2019.00-79 http://dx.doi.org/10.1109/ICMEW.2019.00-79 ]
Kiku D, Monno Y, Tanaka M and Okutomi M. 2013. Residual interpolation for color image demosaicking//Proceedings of 2013 IEEE International Conference on Image Processing. Melbourne, Australia: IEEE: 2304-2308 [ DOI: 10.1109/ICIP.2013.6738475 http://dx.doi.org/10.1109/ICIP.2013.6738475 ]
Kiku D, Monno Y, Tanaka M and Okutomi M. 2014. Minimized-Laplacian residual interpolation for color image demosaicking//Proceedings Volume 9023, Digital Photography X. Electronic Imaging. San Francisco, USA: SPIE: 197-204 [ DOI: 10.1117/12.2038425 http://dx.doi.org/10.1117/12.2038425 ]
Kim J, Lee J K and Lee K M. 2016. Accurate image super-resolution usingvery deep convolutional networks//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE: 1646-1654 [ DOI: 10.1109/CVPR.2016.182 http://dx.doi.org/10.1109/CVPR.2016.182 ]
Kim J S, Ko K and Kim C S. 2020. Adaptive lattice-aware image demosaicking using global and local information//Proceedings of 2020 IEEE International Conference on Image Processing. Abu Dhabi, United Arab Emirates: IEEE: 483-487 [ DOI: 10.1109/ICIP40778.2020.9190936 http://dx.doi.org/10.1109/ICIP40778.2020.9190936 ]
Klambauer G, Unterthiner T, Mayr A and Hochreiter S. 2017. Self-normalizing neural networks [EB/OL ] . [2021-10-29 ] . https://arxiv.org/pdf/1706.02515.pdf https://arxiv.org/pdf/1706.02515.pdf
Kokkinos F and Lefkimmiatis S. 2018. Deep image demosaicking using a cascade of convolutional residual denoising networks//Proceedings of the 15th European Conference on Computer Vision. Munich, Germany: Springer: 317-333 [ DOI: 10.1007/978-3-030-01264-9_19 http://dx.doi.org/10.1007/978-3-030-01264-9_19 ]
Kokkinos F and Lefkimmiatis S. 2019. Iterative joint image demosaicking and denoising using a residual denoising network. IEEE Transactions on Image Processing, 28(8): 4177-4188 [DOI: 10.1109/TIP.2019.2905991]
Lei P C, Liu C, Tang J G and Peng D L. 2020. Hierarchical feature fusion attention network for image super-resolution reconstruction. Journal of Image and Graphics, 25(9): 1773-1786
雷鹏程, 刘丛, 唐坚刚, 彭敦陆. 2020. 分层特征融合注意力网络图像超分辨率重建. 中国图象图形学报, 25(9): 1773-1786) [DOI: 10.11834/jig.190607]
Li J S J and Randhawa S. 2007. Colour filter array demosaicking using cubic spline interpolation//Proceedings of 2007 IEEE International Conference on Acoustics, Speech, and Signal Processing. Honolulu, USA: IEEE: I-865-I-868 [ DOI: 10.1109/ICASSP.2007.366045 http://dx.doi.org/10.1109/ICASSP.2007.366045 ]
Liu J, Zhang W J, Tang Y T, Tang J and Wu G S. 2020a. Residual feature aggregation network for image super-resolution//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE: 2356-2365 [ DOI: 10.1109/CVPR42600.2020.00243 http://dx.doi.org/10.1109/CVPR42600.2020.00243 ]
Liu L, Jia X, Liu J Z and Tian Q. 2020b. Joint demosaicing and denoising with self guidance//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE: 2237-2246 [ DOI: 10.1109/CVPR42600.2020.00231 http://dx.doi.org/10.1109/CVPR42600.2020.00231 ]
Longère P, Zhang X M, Delahunt P B and Brainard D H. 2002. Perceptual assessment of demosaicing algorithm performance. Proceedings of the IEEE, 90(1): 123-132 [DOI: 10.1109/5.982410]
Luo J R and Wang J. 2020. Image demosaicing based on generative adversarial network. Mathematical Problems in Engineering, 2020: #7367608 [DOI: 10.1155/2020/7367608]
Luo J R, Wang J and Yue G D. 2021. CFA image demosaicing algorithm based on generative adversarial network. Computer Engineering, 47(7): 249-256, 265
罗静蕊, 王婕, 岳广德. 2021. 基于生成对抗网络的CFA图像去马赛克算法. 计算机工程, 47(7): 249-256, 265) [DOI: 10.19678/j.issn.1000-3428.0058242]
Mei Y Q, Fan Y C, Zhang Y L, Yu J H, Zhou Y Q, Liu D, Fu Y, Huang T S and Shi H. 2020. Pyramid attention networks for image restoration [EB/OL ] . [2021-10-29 ] . https://arxiv.org/pdf/2004.13824v4.pdf https://arxiv.org/pdf/2004.13824v4.pdf
Monno Y, Kiku D, Tanaka M and Okutomi M. 2015. Adaptive residual interpolation for color image demosaicking//Proceedings of 2015 IEEE International Conference on Image Processing. Quebec City, Canada: IEEE: 3861-3865 [ DOI: 10.1109/ICIP.2015.7351528 http://dx.doi.org/10.1109/ICIP.2015.7351528 ]
Niu Y and Ouyang J H. 2020. Cross-channel correlation preserved three-stream lightweight CNNs for demosaicking [EB/OL ] . [2021-10-29 ] . https://arxiv.org/pdf/1906.09884v2.pdf https://arxiv.org/pdf/1906.09884v2.pdf
Park B and Jeong J. 2018. Image demosaicking using densely connected convolutional neural network//Proceedings of the 14th International Conference on Signal-Image Technology and Internet-Based Systems. Las Palmas de Gran Canaria, Spain: IEEE: 304-307 [ DOI: 10.1109/SITIS.2018.00053 http://dx.doi.org/10.1109/SITIS.2018.00053 ]
Park B and Jeong J. 2019. Color filter array demosaicking using densely connected residual network. IEEE Access, 7: 128076-128085 [DOI: 10.1109/ACCESS.2019.2939578]
Park Y, Lee S, Jeong B and Yoon J. 2020. Joint demosaicing and denoising based on a variational deep image prior neural network. Sensors, 20(10): #2970 [DOI: 10.3390/s20102970]
Pekkucuksen I and Altunbasak Y. 2010. Gradient based threshold free color filter array interpolation//Proceedings of 2010 IEEE International Conference on Image Processing. Hong Kong, China: IEEE: 137-140 [ DOI: 10.1109/ICIP.2010.5654327 http://dx.doi.org/10.1109/ICIP.2010.5654327 ]
Prakash V N V S, Prasad K S and Prasad T J. 2017. Deep learning approach for image denoising and image demosaicing. International Journal of Computer Applications, 168(9): 18-26 [DOI: 10.5120/ijca2017914500]
Qian G C, Gu J J, Ren J S, Dong C, Zhao F R and Lin J. 2021. Trinity of pixel enhancement: a joint solution for demosaicking, denoising and super-resolution [EB/OL ] . [2021-10-29 ] . https://arxiv.org/pdf/1905.02538v1.pdf https://arxiv.org/pdf/1905.02538v1.pdf
Ramanath R, Snyder W E, Bilbro G L and Sander W A. 2002. Demosaicking methods for Bayer color arrays. Journal of Electronic Imaging, 11(3): 306-315 [DOI: 10.1117/1.1484495]
Rafinazari M and Dubois E. 2014. Demosaicking algorithm for the Fujifilm X-Trans color filter array//Proceedings of 2014 IEEE International Conference on Image Processing. Paris, France: IEEE: 660-663 [ DOI: 10.1109/ICIP.2014.7025132 http://dx.doi.org/10.1109/ICIP.2014.7025132 ]
Ronneberger O, Fischer P and Brox T. 2015. U-Net: convolutional networks for biomedical image segmentation//Proceedings of the 18th International Conference on Medical Image Computing and Computer Assisted Intervention. Munich, Germany: Springer: 234-241 [ DOI: 10.1007/978-3-319-24574-4_28 http://dx.doi.org/10.1007/978-3-319-24574-4_28 ]
Sharif S M A, Naqvi R A and Biswas M. 2021. Beyond joint demosaicking and denoising: an image processing pipeline for a pixel-bin image sensor//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Nashville, USA: IEEE: 233-242 [ DOI: 10.1109/CVPRW53098.2021.00032 http://dx.doi.org/10.1109/CVPRW53098.2021.00032 ]
Shi W Z, Caballero J, Huszár F, Totz J, Aitken A P, Bishop R, Rueckert D and Wang Z H. 2016. Real-Time single image and video super-resolution using an efficient sub-pixel convolutional neural network//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE: 1874-1883 [ DOI: 10.1109/CVPR.2016.207 http://dx.doi.org/10.1109/CVPR.2016.207 ]
Syu N S, Chen Y S and Chuang Y Y. 2018. Learning deep convolutional networks for demosaicing [EB/OL ] . [2021-10-29 ] . https://arxiv.org/pdf/1802.03769.pdf https://arxiv.org/pdf/1802.03769.pdf
Szegedy C, Ioffe S, Vanhoucke V and Alemi A A. 2017. Inception-v4, Inception-ResNet and the impact of residual connections on learning//Proceedings of the 31st AAAI Conference on Artificial Intelligence. San Francisco, USA: AAAI Press: 4278-4284
Tan D S, Chen W Y and Hua K L. 2018. DeepDemosaicking: adaptive image demosaicking via multiple deep fully convolutional networks. IEEE Transactions on Image Processing, 27(5): 2408-2419 [DOI: 10.1109/TIP.2018.2803341]
Tan R X, Zhang K, Zuo W and Zhang L. 2017. Color image demosaicking via deep residual learning//Proceedings of 2017 IEEE International Conference on Multimedia and Expo. Hong Kong, China: IEEE: 793-798
Tan Y F, Chang K, Li H X, Tang Z H and Qin T F. 2020. Lightweight color image demosaicking with multi-core feature extraction//Proceedings of 2020 IEEE International Conference on Visual Communications and Image Processing. Macau, China: IEEE: 136-139 [ DOI: 10.1109/VCIP49819.2020.9301841 http://dx.doi.org/10.1109/VCIP49819.2020.9301841 ]
Verma D, Kumar M and Eregala S. 2020. Deep demosaicing using ResNet-Bottleneck architecture//Proceedings of the 4th International Conference on Computer Vision and Image Processing. Jaipur, India: Springer: 170-179 [ DOI: 10.1007/978-981-15-4018-9_16 http://dx.doi.org/10.1007/978-981-15-4018-9_16 ]
Wang H L, Han Z H, Li L, Qiu S and Jin W Q. 2021. Residual and high-frequency replacement based color reconstruction method for SONY-RGBW array. Laser and Optoelectronics Progress, 58(20): #2004001
王海琳, 韩正昊, 李力, 裘溯, 金伟其. 2021. 基于残差和高频替换的SONY-RGBW阵列彩色重构方法. 激光与光电子学进展, 58(20): #2004001)
Wang S Y, Zhao M X, Dou R J, Yu S M, Liu L Y and Wu N J. 2021a. A compact high-quality image demosaicking neural network for edge-computing devices. Sensors, 21(9): #3265 [DOI: 10.3390/s21093265]
Wang Y, Yin S Y, Zhu S Y, Ma Z, Xiong R Q and Zeng B. 2021b. NTSDCN: new three-stage deep convolutional image demosaicking network. IEEE Transactions on Circuits and Systems for Video Technology, 31(9): 3725-3729 [DOI: 10.1109/tcsvt.2020.3040082]
Wan S D, Tang S, Xie X Z, Gu J, Huang R, Ma B and Luo L. 2021. Deep convolutional-neural-network-based channel attention for single image dynamic scene blind deblurring. IEEE Transactions on Circuits and Systems for Video Technology, 31(8): 2994-3009 [DOI: 10.1109/TCSVT.2020.3035664]
Wu C Z, Chen X, Ji D and Zhan S. 2018. Image denoising via residual network based on perceptual loss. Journal of Image and Graphics, 23(10): 1483-1491
吴从中, 陈曦, 季栋, 詹曙. 2018. 结合深度残差学习和感知损失的图像去噪. 中国图象图形学报, 23(10): 1483-1491) [DOI: 10.11834/jig.180069]
Wu D, Zhao H T and Zheng S B. 2020. Motion deblurring method based on DenseNets. Journal of Image and Graphics, 25(5): 890-899
吴迪, 赵洪田, 郑世宝. 2020. 密集连接卷积网络图像去模糊. 中国图象图形学报, 25(5): 890-899) [DOI: 10.11834/jig.190400]
Xie S N, Girshick R B, Dollár P, Tu Z W and He K M. 2017. Aggregated residual transformations for deep neural networks//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE: 5987-5995 [ DOI: 10.1109/CVPR.2017.634 http://dx.doi.org/10.1109/CVPR.2017.634 ]
Xing W Z and Egiazarian K. 2021. End-to-End learning for joint image demosaicing, denoising and super-resolution//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, USA: IEEE: 3506-3515 [ DOI: 10.1109/CVPR46437.2021.00351 http://dx.doi.org/10.1109/CVPR46437.2021.00351 ]
Xu X, Ye Y F and Li X. 2020. Joint demosaicing and super-resolution (JDSR): network design and perceptual optimization. IEEE Transactions on Computational Imaging, 6: 968-980 [DOI: 10.1109/TCI.2020.2999819]
Ye W and Ma K K. 2015. Color image demosaicing using iterative residual interpolation. IEEE Transactions on Image Processing, 24(12): 5879-5891 [DOI: 10.1109/TIP.2015.2482899]
Yu J H and Yang X M. 2021. Double branch residual network for demosaicing. Laser and Optoelectronics Progress, 58(2): #0210012
余继辉, 杨晓敏. 2021. 双分支残差去马赛克网络. 激光与光电子学进展, 58(2): #0210012) [DOI: 10.3788/LOP202158.0210012]
Yu J H, Yang X M and Yan B Y. 2020. Color image demosaicking based on deep convolution neural network. Application Research of Computers, 37(S1): 343-345
余继辉, 杨晓敏, 严斌宇. 2020. 基于深度学习的彩色图像去马赛克. 计算机应用研究, 37(S1): 343-345
Zhang J K, An C and Nguyen T. 2018. Deep joint demosaicing and super resolution on high resolution Bayer sensor data//Proceedings of 2018 IEEE Global Conference on Signal and Information Processing. Anaheim, USA: IEEE: 619-623 [ DOI: 10.1109/GlobalSIP.2018.8646321 http://dx.doi.org/10.1109/GlobalSIP.2018.8646321 ]
Zhang Y L, Li K P, Li K, Zhong B N and Fu Y. 2019. Residual non-local attention networks for image restoration. [EB/OL ] . [2021-10-29 ] . https://arxiv.org/pdf/1903.10082v1.pdf https://arxiv.org/pdf/1903.10082v1.pdf
Zhao Y Z, Po L M, Zhang T T, Liao Z B, Shi X, Zhang Y J, Ou W F, Xian P F, Xiong J J, Zhou C and Yu W Y. 2019. Saliency map-aided generative adversarial network for RAW to RGB mapping//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision Workshop. Seoul, Korea (South): IEEE: 3449-3457 [ DOI: 10.1109/ICCVW.2019.00428 http://dx.doi.org/10.1109/ICCVW.2019.00428 ]
Zhou R F, Achanta R and Süsstrunk S. 2018a. Deep residual network for joint demosaicing and super-resolution [EB/OL ] . [2021-10-29 ] . https://arxiv.org/pdf/1802.06573.pdf https://arxiv.org/pdf/1802.06573.pdf
Zhou Z W, Siddiquee M R, Tajbakhsh N and Liang J M. 2018b. UNet++: a nested U-Net architecture for medical image segmentation//Proceedings of the 4th International Workshop, DLMIA 2018, and the 8th International Workshop, ML-CDS 2018. Granada, Spain: Springer: 3-11 [ DOI: 10.1007/978-3-030-00889-5_1 http://dx.doi.org/10.1007/978-3-030-00889-5_1 ]
相关文章
相关作者
相关机构
京公网安备11010802024621
