摘要
超分辨率图像可以提供更丰富的纹理细节信息,在机器视觉应用领域中占有重要的地位,已成为机器视觉领域的一个研究热点。利用深度学习技术,设计一个深度卷积神经网络,实现从低分辨率图像到高分辨率图像的非线性映射,从而实现图像的超分辨率重建。通过实验,将所设计的网络模型与一些前沿的方法进行了定性和定量的比较,实验结果表明设计的网络模型具有明显的优越性。
Single image super-resolution(SISR) has attracted great attentions due to it can offer more details that may play a critical role in various machine vision tasks. In this paper, a deep convolutional neural networks is proposed to address the SISR problem via the deep learning technique, which has a powerful capability for achieving the non-linear mapping between low and high resolution images. We compare our method with some state-of-the-arts in the experimental section. The results demonstrate that the proposed model achieves a notable improvement in terms of both quantitative and qualitative measurements.
引文
[1] IRANI M,PELEG S.Improving resolution by image registration[J].CVGIP:Graphical Models and Image Processing,1991,53(3):231-239.
[2] SUN J,XU Z B,SHUM H Y.Gradient profile prior and its applications in image super-resolution and enhancement[J].IEEE Transactions on Image Processing,2011,20(6):1 529.
[3] YANG J,WRIGHT,T,HUANG,T S,et al.Image super-resolution via sparse representation[J].IEEE Transactions on Image Processing,2010(19):2 861-2 873.
[4] HE H,SIU W C.Single image super-resolution using Gaussian process regression[C]//Computer Vision and Pattern Recognition,2011:449-456.
[5] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Image net classification with deep convolutional neural networks[C]//International Conference on Neural Information Processing Systems,2012:1 097-1 105.
[6] DONG C,CHEN C L,HE K,et al.Learning a deep convolutional network for image super-resolution[C]//European Conference on Computer Vision,2014:184-199.
[7] DONG C,LOY C C,HE K,et al.Image super-resolution using deep convolutional networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(2):295-307.
[8] BEVILACQUA M,ROUMY A,GUILLEMOT C,et al.Low-complexity single-Image super-resolution based on nonnegative neighbor embedding[C]//Proceeding of British Machine Vision Conference,2012:1-10.
[9] KIM K I.Single-image super-resolution using sparse regression and natural image prior[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(6):1127-1133.
[10] TIMOFTE R,DE V,VAN G L.Anchored neighborhood regression for fast example-based super-resolution[C]//Proceedings of the IEEE International Conference on Computer Vision,2013:1 920-1 927.
[11] WANG L F,WU H Y,PAN C H.Fast image upsampling via the displacement field[J].IEEE Transactions on Image Processing,2014,23(12):5 123-5 135.