A Hybrid Approach Between Adversarial Generative Networks and Actor-Critic Policy Gradient for Low Rate High-Resolution Image Compression
This work addresses image compression for applications requiring high-quality storage or transmission, but it is incremental as it builds on existing deep learning and reinforcement learning techniques.
The paper tackles low-rate high-resolution image compression by proposing a deep super-resolution workflow that maps low-resolution JPEG images to high-resolution using an encoder-decoder network combined with GANs and reinforcement learning (A3C) to maximize PSNR, achieving competitive results without specifying concrete numbers.
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.