Lossless Image Compression through Super-Resolution
arXiv:2004.02872
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 (8)
- Auto-Encoding Variational Bayes
- Rethinking Atrous Convolution for Semantic Image Segmentation
- Pixel Recurrent Neural Networks
- Variational Inference with Normalizing Flows
- A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets
- Asymmetric numeral systems
- Parallel Multiscale Autoregressive Density Estimation
- Compression with Flows via Local Bits-Back Coding
Cited by in corpus (7)
- IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression
- Efficient Visual Computing with Camera RAW Snapshots
- L3C-Stereo: Lossless Compression for Stereo Images
- Joint Semi-supervised 3D Super-Resolution and Segmentation with Mixed Adversarial Gaussian Domain Adaptation
- PixelPyramids: Exact Inference Models from Lossless Image Pyramids
- iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression
- Learning to Learn to Compress