基于多尺度递归网络的图像超分辨率重建

吴磊; 吕国强; 薛治天; 盛杰超; 冯奇斌

doi:doi:10.3788/AOS201939.0610001

光学学报, 2019, 39 (6): 0610001, 网络出版: 2019-06-17

基于多尺度递归网络的图像超分辨率重建下载： 1775次

Super-Resolution Reconstruction of Images Based on Multi-Scale Recursive Network

论文大纲

吴磊 ^1,2吕国强 ^2,3薛治天 ^1,2盛杰超 ^2,3冯奇斌 ^2,*

作者单位

¹ 合肥工业大学电子科学与应用物理学院, 安徽合肥 230009

² 合肥工业大学特种显示技术国家工程实验室现代显示技术省部共建国家重点实验室光电技术研究院, 安徽合肥 230009

³ 合肥工业大学仪器科学与光电工程学院, 安徽合肥 230009

图像处理超分辨率多尺度特征卷积神经网络亚像素卷积 image processing super-resolution multi-scale features convolutional neural networks sub-pixel convolution

AI 词云图 AI一句话精读 AI短摘要

注：本部分内容由 AI 自动生成，请您知悉。

摘要

提出了一种基于多尺度递归网络的图像超分辨率网络模型,该模型主要由多个多尺度特征映射单元级联而成,每个单元分别包含一组不同尺度的特征提取层、一个融合层以及一个特征映射层。特征提取直接在原始低分辨率图像上进行,最后采用亚像素卷积重构高分辨率图像。训练阶段使用自适应矩估计优化方法加速网络模型的收敛。实验结果表明,所提算法取得了较好的超分辨率结果,图像纹理清晰、边缘锐利,视觉效果明显得到增强。在Set5、Set14、BSD100以及Urban100等常用测试集上的客观评价指标(PSNR和SSIM)均高于现有的几种主流算法。

Abstract

An image super-resolution network model is proposed based on a multi-scale recursive network herein. The proposed model mainly comprises a plurality of multi-scale feature mapping units, each of which includes a set of feature extraction layers with different scales, a fusion layer, and a mapping layer. The network performs feature extraction directly on an original low-resolution image, which is then reconstructed into a high-resolution image via sub-pixel convolution. In the training phase, the adaptive optimization method is used to accelerate the convergence of the network model. The experimental results show that the proposed algorithm achieves better super-resolution results, significantly improves the subjective visual effects, and sharpens the image texture. The objective evaluation indicators (PSNR and SSIM) of the proposed algorithm on the common test sets such as Set5, Set14, BSD100, and Urban100 are higher than those of the existing mainstream algorithms.

参考文献

[1] Park S C, Park M K and Kang M G. Super-resolution image reconstruction: a technical overview. IEEE Signal Processing Magazine. 20(3), 21-36(2003).

[2] Wang M, Liu K X, Liu L et al. Super-resolution reconstruction of image based on optimized convolution neural network. Laser & Optoelectronics Progress. 54(11), (2017).
王民, 刘可心, 刘利等. 基于优化卷积神经网络的图像超分辨率重建. 激光与光电子学进展. 54(11), (2017).

[4] Li X and Orchard M T. New edge-directed interpolation. IEEE Transactions on Image Processing. 10(10), 1521-1527(2001).

[5] Unser M, Aldroubi A and Eden M. Fast B-spline transforms for continuous image representation and interpolation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 13(3), 277-285(1991).

[6] Schultz R R and Stevenson R L. Extraction of high-resolution frames from video sequences. IEEE Transactions on Image Processing. 5(6), 996-1011(1996).

[7] Sun J, Xu Z B and Shum H Y. Image super-resolution using gradient profile prior. [C]∥2008 IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2008, Anchorage, AK, USA. New York: IEEE. 4587659, (2008).

[8] Irani M and Peleg S. Improving resolution by image registration. CVGIP: Graphical Models and Image Processing. 53(3), 231-239(1991).

[9] Stark H and Oskoui P. High-resolution image recovery from image-plane arrays, using convex projections. Journal of the Optical Society of America A. 6(11), 1715-1726(1989).

[10] Timofte R, De V and Gool L V. Anchored neighborhood regression for fast example-based super-resolution. [C]∥2013 IEEE International Conference on Computer Vision, December 1-8, 2013, Sydney, NSW, Australia. New York: IEEE. 1920-1927(2013).

[11] Chang H, Yeung D Y and Xiong Y M. Super-resolution through neighbor embedding. [C]∥Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004, June 27-July 2, 2004, Washington D. C., USA. New York: IEEE. 1315043, (2004).

[12] Huang J B, Singh A and Ahuja N. Single image super-resolution from transformed self-exemplars. [C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: IEEE. 5197-5206(2015).

[13] Freeman W T, Jones T R and Pasztor E C. Example-based super-resolution. IEEE Computer Graphics and Applications. 22(2), 56-65(2002).

[14] Yang J C, Wright J, Huang T et al. Image super-resolution as sparse representation of raw image patches. [C]∥2008 IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2008, Anchorage, AK, USA. New York: IEEE. 14587647, (2008).

[15] Dong C, Loy C C, He K M et al. Learning a deep convolutional network for image super-resolution. ∥Fleet D, Pajdla T, Schiele B, et al. Computer Vision-ECCV 2014. Cham: Springer. 8692, 184-199(2014).

[16] Dong C, Loy C C and Tang X O. Accelerating the super-resolution convolutional neural network. ∥Leibe B, Matas J, Sebe N, et al. Computer Vision-ECCV 2016. Cham: Springer. 9906, 391-407(2016).

[17] Kim J, Lee J K and Lee K M. Accurate image super-resolution using very deep convolutional networks. [C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 1646-1654(2016).

[18] 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]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 1874-1883(2016).

[19] Xiao J S, Liu E Y, Zhu L et al. Improved image super-resolution algorithm based on convolutional neural network. Acta Optica Sinica. 37(3), (2017).
肖进胜, 刘恩雨, 朱力等. 改进的基于卷积神经网络的图像超分辨率算法. 光学学报. 37(3), (2017).

[21] Du B, Xiong W, Wu J et al. Stacked convolutional denoising auto-encoders for feature representation. IEEE Transactions on Cybernetics. 47(4), 1017-1027(2017).

[22] Sun C, Lü J W, Li J W et al. Method of rapid image super-resolution based on deconvolution. Acta Optica Sinica. 37(12), (2017).
孙超, 吕俊伟, 李健伟等. 基于去卷积的快速图像超分辨率方法. 光学学报. 37(12), (2017).

[24] Deng C, Xu J, Zhang K B et al. Similarity constraints-based structured output regression machine: an approach to image super-resolution. IEEE Transactions on Neural Networks and Learning Systems. 27(12), 2472-2485(2016).

[25] 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 Eighth IEEE International Conference on Computer Vision, July 7-14, 2001, Vancouver, BC, Canada. New York: IEEE. 416-423(2001).

[26] Fan X X, Yang Y H, Deng C et al. Compressed multi-scale feature fusion network for single image super-resolution. Signal Processing. 146, 50-60(2018).

[27] Su H, Zhou J and Zhang Z H. Survey of super-resolution image reconstruction methods. Acta Automatica Sinica. 39(8), 1202-1213(2013).
苏衡, 周杰, 张志浩. 超分辨率图像重建方法综述. 自动化学报. 39(8), 1202-1213(2013).

吴磊, 吕国强, 薛治天, 盛杰超, 冯奇斌. 基于多尺度递归网络的图像超分辨率重建[J]. 光学学报, 2019, 39(6): 0610001. Lei Wu, Guoqiang Lü, Zhitian Xue, Jiechao Sheng, Qibin Feng. Super-Resolution Reconstruction of Images Based on Multi-Scale Recursive Network[J]. Acta Optica Sinica, 2019, 39(6): 0610001.

基于多尺度递归网络的图像超分辨率重建下载： 1775次

关于本站 Cookie 的使用提示

全站搜索

基于多尺度递归网络的图像超分辨率重建 下载： 1775次

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索

基于多尺度递归网络的图像超分辨率重建下载： 1775次