Lossless Image Compression through Super-Resolution

Abstract

We introduce a simple and efficient lossless image compression algorithm. We store a low resolution version of an image as raw pixels, followed by several iterations of lossless super-resolution. For lossless super-resolution, we predict the probability of a high-resolution image, conditioned on the low-resolution input, and use entropy coding to compress this super-resolution operator. Super-Resolution based Compression (SReC) is able to achieve state-of-the-art compression rates with practical runtimes on large datasets. Code is available online at https://github.com/caoscott/SReC.

Tech report

References in corpus (4)

• Rethinking Atrous Convolution for Semantic Image Segmentation
• A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets
• Asymmetric numeral systems
• Parallel Multiscale Autoregressive Density Estimation