Deep Image Compression via End-to-End Learning

TL;DR

This paper introduces a deep CNN-based image compression method that surpasses traditional codecs in visual quality at the same bit rate, using perceptual and adversarial training techniques for improved results.

Contribution

The authors propose a novel end-to-end deep learning framework with perceptual and adversarial losses, along with transfer learning for better rate-distortion optimization, outperforming existing codecs.

Findings

Achieves higher MS-SSIM than BPG, WebP, JPEG2000, JPEG

Reduces BD-rate by 7.81% on Kodak dataset

Reduces BD-rate by 19.1% on ETH Zurich dataset

Abstract

We present a lossy image compression method based on deep convolutional neural networks (CNNs), which outperforms the existing BPG, WebP, JPEG2000 and JPEG as measured via multi-scale structural similarity (MS-SSIM), at the same bit rate. Currently, most of the CNNs based approaches train the network using a L2 loss between the reconstructions and the ground-truths in the pixel domain, which leads to over-smoothing results and visual quality degradation especially at a very low bit rate. Therefore, we improve the subjective quality with the combination of a perception loss and an adversarial loss additionally. To achieve better rate-distortion optimization (RDO), we also introduce an easy-to-hard transfer learning when adding quantization error and rate constraint. Finally, we evaluate our method on public Kodak and the Test Dataset P/M released by the Computer Vision Lab of ETH Zurich, resulting in averaged 7.81% and 19.1% BD-rate reduction over BPG, respectively.