Extreme Image Coding via Multiscale Autoencoders With Generative Adversarial Optimization
This addresses the problem of visually pleasing image compression for low-bandwidth applications, though it appears incremental as it builds on existing autoencoder and GAN techniques.
The paper tackles extreme image compression at very low bitrates by proposing a MultiScale AutoEncoder (MSAE) framework with GAN optimization, achieving significant subjective quality improvements over HEVC and JPEG2000 on Cityscapes and ADE20K datasets.
We propose a MultiScale AutoEncoder(MSAE) based extreme image compression framework to offer visually pleasing reconstruction at a very low bitrate. Our method leverages the "priors" at different resolution scale to improve the compression efficiency, and also employs the generative adversarial network(GAN) with multiscale discriminators to perform the end-to-end trainable rate-distortion optimization. We compare the perceptual quality of our reconstructions with traditional compression algorithms using High-Efficiency Video Coding(HEVC) based Intra Profile and JPEG2000 on the public Cityscapes and ADE20K datasets, demonstrating the significant subjective quality improvement.