基于空间变换网络的图像超分辨率重建Image super-resolution reconstruction using spatial transformation network
刘颖;朱丽;林庆帆;
摘要(Abstract):
提出一种基于空间变换网络的图像超分辨率重建算法。通过设计空间变换网络,学习合适的变换参数进而对齐原始图像;利用视觉注意机制扩充网络,在训练过程中自动选择感兴趣的区域特征。最后,利用生成对抗网络进行超分辨率图像重建,从而达到高分辨率图像重建的目的。与其他算法在数据集上的重建效果对比结果表明,所提算法的超分辨率重建效果较好,且评价指数均有所提高。
关键词(KeyWords): 超分辨率重建;空间变换网络;生成对抗网络
基金项目(Foundation): 国家自然科学基金项目(61802305);; 公安部科技强警专项项目(2016GABJC51)
作者(Author): 刘颖;朱丽;林庆帆;
Email:
DOI: 10.13682/j.issn.2095-6533.2020.05.008
参考文献(References):
- [1] 刘颖,朱丽,林庆帆,等.图像超分辨率技术的回顾与展望[J].计算机科学与探索,2020,14(2):181-199.DOI:10.3778/j.issn.1673-9418.1909057.
- [2] 刘颖,权婉,伍世虔.基于边缘增强的正则化超分辨率图像重建[J].西安邮电大学学报,2016,21(6):14-19.DOI:10.13682/j.issn.2095-6533.2016.06.003.
- [3] HUANG Y,SHAO L,FRANGI A F.Simultaneous super-resolution and cross-modality synthesis of 3D medical images using weakly-supervised joint convolutional sparse coding[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Hawaii:IEEE,2017:6070-6079.
- [4] RASTI P,UIBOUPIN T,ESCALERA S,et al.Convolutional neural network super resolution for face recognition in surveillance monitoring[C]//Proceedings of International Conference on Articulated Motion and Deformable Objects.Palma de Mallorca:Springer International Publishing,2016:175-184.DOI:10.1007/978-3-319-41778-3_18.
- [5] ZHANG H,LIU D,XIONG Z.Convolutional neural network-based video super-resolution for action recognition[C]//Proceedings of 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition.Xi'an:IEEE,2018:746-750.DOI:10.1109/FG.2018.00117.
- [6] BAI Y,ZHANG Y,DING M,et al.Sod-mtgan:Small object detection via multi-task generative adversarial network[C]//Proceedings of the European Conference on Computer Vision.Munich:Springer-Verlag,2018:206-221.DOI:10.1007/978-3-030-01261-8_13.
- [7] DONG C,LOY C C,HE K,et al.Learning a deep convolutional network for image super-resolution[C]//Proceedings of European Conference on Computer Vision.Switzerland:Springer-Verlag,2014:184-199.DOI:10.1007/978-3-319-10593-2_13.
- [8] 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,2015,38(2):295-307.DOI:10.1109/TPAMI.2015.2439281.
- [9] GOODFELLOW I,POUGET-ABADIE J,MIRZA M,et al.Generative adversarial nets[C]//Proceedings of Advances in Neural Information Processing Systems.Quebec:NIPS Proceedings,2014:2672-2680.DOI:10.5555/2969033.2969125.
- [10] LEDIG C,THEIS L,HUSZAR 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.Hawaii:IEEE,2017:4681-4690.DOI:10.1109/CVPR.2017.19.
- [11] JADERBERG M,SIMONYYAN K,ZISSERMAN A.Spatial transformer networks[C]//Proceedings of Advances in neural information processing systems.Quebe:Advances in Neural Information,2015:2017-2025.
- [12] HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition.Nevada:IEEE,2016:770-77.DOI:10.1109/CVPR.2016.90.
- [13] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[C]//Proceedings of International Conference on Learning Representations 2015.[S.l.]:arXiv preprin,2015:665-674.
- [14] SHI W Z,CABALLERO J,HUSZAR F,et al.Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE,2016:1874-1883.DOI:10.1109/CVPR.2016.207.
- [15] WANG Z,CHANG S,YANG Y,et al.Studying very low resolution recognition using deep networks[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE,2016:4792-4800.DOI:10.1109/CVPR.2016.518.
- [16] HEIKH H R,BOVIK A C,VECIANA G D.An information fidelity criterion for image quality assessment using natural scene statistics[J].IEEE Transactions on Image Processing,2005,14(12):2117-2128.DOI:10.1109/TIP.2005.859389.