Enhancing Digital Zoom in Mobile Phone Cameras by Low Complexity Super-Resolution

In this paper, we present an enhancement method for improvement of digital zoom feature in mobile phone cameras. The enhancement approach is based on the state-of-the-art deep learning-based super-resolution. We introduce an input super-pixel pooling layer in the enhancement framework, that down-scales the input data without losing information, and results in a 96% complexity reduction of the enhancement framework, when compared with the baseline approach. The presented model is also capable of being trained simultaneously for several scaling factors and different levels of enhancement, without affecting the complexity of the approach.

[1]  Shiguang Shan,et al.  Deep Network Cascade for Image Super-resolution , 2014, ECCV.

[2]  Daniel Rueckert,et al.  Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Kyoung Mu Lee,et al.  Deeply-Recursive Convolutional Network for Image Super-Resolution , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Eirikur Agustsson,et al.  NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[5]  Thomas S. Huang,et al.  Self-tuned deep super resolution , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[6]  Xiaoou Tang,et al.  Accelerating the Super-Resolution Convolutional Neural Network , 2016, ECCV.

[7]  Xiaoou Tang,et al.  Learning a Deep Convolutional Network for Image Super-Resolution , 2014, ECCV.

[8]  Touradj Ebrahimi,et al.  Ultra-eye: UHD and HD images eye tracking dataset , 2014, 2014 Sixth International Workshop on Quality of Multimedia Experience (QoMEX).

[9]  Kyoung Mu Lee,et al.  Accurate Image Super-Resolution Using Very Deep Convolutional Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[11]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[12]  Yu-Bin Yang,et al.  Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections , 2016, NIPS.