Lossless Image Compression through Super-Resolution
This addresses the problem of efficient lossless image compression for applications requiring high fidelity, though it appears incremental as it builds on super-resolution techniques.
The paper tackles lossless image compression by storing a low-resolution image and applying lossless super-resolution, achieving state-of-the-art compression rates with practical runtimes on large datasets.
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.