# Practical Full Resolution Learned Lossless Image Compression

arXiv: https://arxiv.org/abs/1811.12817 · HTML: https://mlsanity.com/paper/1811.12817/

## Key facts

- Cited by 94 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2018.

## Built on by (most cited first, 30 of 94)

- [Language Modeling Is Compression](https://mlsanity.com/paper/2309.10668/) (2023)
- [Autoregressive Diffusion Models](https://mlsanity.com/paper/2110.02037/) (2021)
- [CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving](https://mlsanity.com/paper/2310.07240/) (2023)
- [Image and Video Tokenization with Binary Spherical Quantization](https://mlsanity.com/paper/2406.07548/) (2024)
- [An Introduction to Neural Data Compression](https://mlsanity.com/paper/2202.06533/) (2022)
- [HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation](https://mlsanity.com/paper/2306.09818/) (2023)
- [Image coding for machines: an end-to-end learned approach](https://mlsanity.com/paper/2108.09993/) (2021)
- [Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules](https://mlsanity.com/paper/2107.06463/) (2021)
- [On the Out-of-distribution Generalization of Probabilistic Image Modelling](https://mlsanity.com/paper/2109.02639/) (2021)
- [iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression](https://mlsanity.com/paper/2103.16211/) (2021)
- [iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Coder](https://mlsanity.com/paper/2111.00965/) (2021)
- [Image Compression for Machine and Human Vision with Spatial-Frequency Adaptation](https://mlsanity.com/paper/2407.09853/) (2024)
- [Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression](https://mlsanity.com/paper/2209.04847/) (2022)
- [CRA5: Extreme Compression of ERA5 for Portable Global Climate and Weather Research via an Efficient Variational Transformer](https://mlsanity.com/paper/2405.03376/) (2024)
- [Multiscale deep context modeling for lossless point cloud geometry compression](https://mlsanity.com/paper/2104.09859/) (2021)
- [Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations](https://mlsanity.com/paper/2008.09662/) (2020)
- [Lossless Compression with Probabilistic Circuits](https://mlsanity.com/paper/2111.11632/) (2021)
- [RIDDLE: Lidar Data Compression with Range Image Deep Delta Encoding](https://mlsanity.com/paper/2206.01738/) (2022)
- [Efficient Visual Computing with Camera RAW Snapshots](https://mlsanity.com/paper/2212.07778/) (2022)
- [Learning Scalable ℓ_∞-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression](https://mlsanity.com/paper/2103.17015/) (2021)
- [Large Language Model for Lossless Image Compression with Visual Prompts](https://mlsanity.com/paper/2502.16163/) (2025)
- [Attention-based Convolutional Autoencoders for 3D-Variational Data Assimilation](https://mlsanity.com/paper/2101.02121/) (2021)
- [Learned Image Compression for Machine Perception](https://mlsanity.com/paper/2111.02249/) (2021)
- [Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data](https://mlsanity.com/paper/2410.05078/) (2024)
- [LC-FDNet: Learned Lossless Image Compression with Frequency Decomposition Network](https://mlsanity.com/paper/2112.06417/) (2021)
- [aiWave: Volumetric Image Compression with 3-D Trained Affine Wavelet-like Transform](https://mlsanity.com/paper/2203.05822/) (2022)
- [Partition and Code: learning how to compress graphs](https://mlsanity.com/paper/2107.01952/) (2021)
- [UDC: Unified DNAS for Compressible TinyML Models](https://mlsanity.com/paper/2201.05842/) (2022)
- [Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You Need](https://mlsanity.com/paper/2411.12448/) (2024)
- [Bit Allocation using Optimization](https://mlsanity.com/paper/2209.09422/) (2022)

## Abstract (arXiv)

We propose the first practical learned lossless image compression system, L3C, and show that it outperforms the popular engineered codecs, PNG, WebP and JPEG 2000. At the core of our method is a fully parallelizable hierarchical probabilistic model for adaptive entropy coding which is optimized end-to-end for the compression task. In contrast to recent autoregressive discrete probabilistic models such as PixelCNN, our method i) models the image distribution jointly with learned auxiliary representations instead of exclusively modeling the image distribution in RGB space, and ii) only requires three forward-passes to predict all pixel probabilities instead of one for each pixel. As a result, L3C obtains over two orders of magnitude speedups when sampling compared to the fastest PixelCNN variant (Multiscale-PixelCNN). Furthermore, we find that learning the auxiliary representation is crucial and outperforms predefined auxiliary representations such as an RGB pyramid significantly.