Effective Utilization of Hybrid Residual Modules in Deep Neural Networks for Super Resolution

Recently, Single-Image Super-Resolution (SISR) has attracted a lot of researchers due to its numerous real-life applications in multiple domains. This paper focuses on efficient solutions of SISR with Hybrid Residual Modules (HRM). The proposed HRM allows the deep neural network to reconstruct very high quality super-resolved images with much lower computation compared to the conventional SISR methods. In this paper, we first describe the technical details of our HRM in SISR and introduce interesting applications of the proposed SISR method, such as surveillance camera system, medical imaging, astronomical imaging.

[1]  Sung-Ho Bae,et al.  HRAN: Hybrid Residual Attention Network for Single Image Super-Resolution , 2019, IEEE Access.

[2]  Zhongyuan Wang,et al.  Video Satellite Imagery Super Resolution via Convolutional Neural Networks , 2017, IEEE Geoscience and Remote Sensing Letters.

[3]  Shutao Li,et al.  Infrared surveillance image super resolution via group sparse representation , 2013 .

[4]  Jun Fang,et al.  Super-Resolution Channel Estimation for MmWave Massive MIMO With Hybrid Precoding , 2017, IEEE Transactions on Vehicular Technology.

[5]  M. Tanter,et al.  Ultrafast ultrasound localization microscopy for deep super-resolution vascular imaging , 2015, Nature.

[6]  Bir Bhanu,et al.  Super resolution for astronomical observations , 2018 .

[7]  Hayit Greenspan,et al.  Super-Resolution in Medical Imaging , 2009, Comput. J..

[8]  Kangfu Mei,et al.  Multi-scale Residual Network for Image Super-Resolution , 2018, ECCV.

[9]  Dwarikanath Mahapatra,et al.  Image Super Resolution Using Generative Adversarial Networks and Local Saliency Maps for Retinal Image Analysis , 2017, MICCAI.

[10]  Chi-Hieu Pham,et al.  Brain MRI super-resolution using deep 3D convolutional networks , 2017, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).

[11]  Chiman Kwan,et al.  A joint sparsity approach to tunnel activity monitoring using high resolution satellite images , 2017, 2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON).

[12]  Hugh G. Lewis,et al.  Super-resolution target identification from remotely sensed images using a Hopfield neural network , 2001, IEEE Trans. Geosci. Remote. Sens..

[13]  Alberto Diaspro,et al.  The 2015 super-resolution microscopy roadmap , 2015, Journal of Physics D: Applied Physics.

[14]  Peter M. Atkinson,et al.  Sub‐pixel mapping of rural land cover objects from fine spatial resolution satellite sensor imagery using super‐resolution pixel‐swapping , 2006 .

[15]  Soo Ye Kim,et al.  Deep SR-ITM: Joint Learning of Super-Resolution and Inverse Tone-Mapping for 4K UHD HDR Applications , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[16]  Shixue Zhang,et al.  Super-resolution Geometry Processing Technology for Ill-sampled Astronomical Images , 2019 .

[17]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Rui Guo,et al.  Super-resolution from unregistered aliased astronomical images , 2019, J. Electronic Imaging.

[19]  Tomio Goto,et al.  Super-resolution System for 4K-HDTV , 2014, 2014 22nd International Conference on Pattern Recognition.

[20]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Feng Shi,et al.  Brain MRI super resolution using 3D deep densely connected neural networks , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[22]  Mark Bates,et al.  Three-Dimensional Super-Resolution Imaging by Stochastic Optical Reconstruction Microscopy , 2008, Science.

[23]  Kyoung Mu Lee,et al.  Enhanced Deep Residual Networks for Single Image Super-Resolution , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).