A Hybrid Approach Between Adversarial Generative Networks and Actor-Critic Policy Gradient for Low Rate High-Resolution Image Compression

Image compression is an essential approach for decreasing the size in bytes of the image without deteriorating the quality of it. Typically, classic algorithms are used but recently deep-learning has been successfully applied. In this work, is presented a deep super-resolution work-flow for image compression that maps low-resolution JPEG image to the high-resolution. The pipeline consists of two components: first, an encoder-decoder neural network learns how to transform the downsampling JPEG images to high resolution. Second, a combination between Generative Adversarial Networks (GANs) and reinforcement learning Actor-Critic (A3C) loss pushes the encoder-decoder to indirectly maximize High Peak Signal-to-Noise Ratio (PSNR). Although PSNR is a fully differentiable metric, this work opens the doors to new solutions for maximizing non-differential metrics through an end-to-end approach between encoder-decoder networks and reinforcement learning policy gradient methods.

[1]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  David Minnen,et al.  Full Resolution Image Compression with Recurrent Neural Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Eamonn J. Keogh,et al.  Scaling up dynamic time warping for datamining applications , 2000, KDD '00.

[4]  Zhou Wang,et al.  Multiscale structural similarity for image quality assessment , 2003, The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003.

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

[6]  Zhan Ma,et al.  Deep Image Compression via End-to-End Learning , 2018, CVPR Workshops.

[7]  Alex Graves,et al.  Asynchronous Methods for Deep Reinforcement Learning , 2016, ICML.

[8]  Michael W. Marcellin,et al.  JPEG2000 - image compression fundamentals, standards and practice , 2013, The Kluwer international series in engineering and computer science.

[9]  Christian Ledig,et al.  Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize , 2017, ArXiv.

[10]  Luc Van Gool,et al.  Extreme Learned Image Compression with GANs , 2018, CVPR Workshops.