# Lossy Image Compression with Normalizing Flows

arXiv: https://arxiv.org/abs/2008.10486 · HTML: https://mlsanity.com/paper/2008.10486/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Aug 2020.

## Built on by (most cited first, 25 of 25)

- [Enhanced Invertible Encoding for Learned Image Compression](https://mlsanity.com/paper/2108.03690/) (2021)
- [An Introduction to Neural Data Compression](https://mlsanity.com/paper/2202.06533/) (2022)
- [Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs](https://mlsanity.com/paper/2305.03935/) (2023)
- [Idempotence and Perceptual Image Compression](https://mlsanity.com/paper/2401.08920/) (2024)
- [Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuning](https://mlsanity.com/paper/2112.08691/) (2021)
- [ANFIC: Image Compression Using Augmented Normalizing Flows](https://mlsanity.com/paper/2107.08470/) (2021)
- [Raw Image Reconstruction with Learned Compact Metadata](https://mlsanity.com/paper/2302.12995/) (2023)
- [aiWave: Volumetric Image Compression with 3-D Trained Affine Wavelet-like Transform](https://mlsanity.com/paper/2203.05822/) (2022)
- [Robust Simulation-Based Inference in Cosmology with Bayesian Neural Networks](https://mlsanity.com/paper/2207.08435/) (2022)
- [Insights from Generative Modeling for Neural Video Compression](https://mlsanity.com/paper/2107.13136/) (2021)
- [High-Fidelity Variable-Rate Image Compression via Invertible Activation Transformation](https://mlsanity.com/paper/2209.05054/) (2022)
- [Beyond Learned Metadata-based Raw Image Reconstruction](https://mlsanity.com/paper/2306.12058/) (2023)
- [Multi-Scale Invertible Neural Network for Wide-Range Variable-Rate Learned Image Compression](https://mlsanity.com/paper/2503.21284/) (2025)
- [Microdosing: Knowledge Distillation for GAN based Compression](https://mlsanity.com/paper/2201.02624/) (2022)
- [Make Lossy Compression Meaningful for Low-Light Images](https://mlsanity.com/paper/2305.15030/) (2023)
- [Wavelet-Like Transform-Based Technology in Response to the Call for Proposals on Neural Network-Based Image Coding](https://mlsanity.com/paper/2403.05937/) (2024)
- [Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimization](https://mlsanity.com/paper/2405.14221/) (2024)
- [Approximately Invertible Neural Network for Learned Image Compression](https://mlsanity.com/paper/2408.17073/) (2024)
- [iWave3D: End-to-end Brain Image Compression with Trainable 3-D Wavelet Transform](https://mlsanity.com/paper/2109.08942/) (2021)
- [Improving Multi-generation Robustness of Learned Image Compression](https://mlsanity.com/paper/2210.17039/) (2022)
- [Streaming Lossless Volumetric Compression of Medical Images Using Gated Recurrent Convolutional Neural Network](https://mlsanity.com/paper/2311.16200/) (2023)
- [Learned Multimodal Compression for Autonomous Driving](https://mlsanity.com/paper/2408.08211/) (2024)
- [High-Fidelity Video Compression based on Invertible Neural Transform and Implicit Conditioning](https://mlsanity.com/paper/2606.13957/) (2026)
- [ChebBooster: A Training-Free Approach for Efficient Diffusion Transformer Inference via Chebyshev-Inspired Extrapolation](https://mlsanity.com/paper/2608.23429/) (2026)
- [Memory-Efficient Training-Free Acceleration of Diffusion Transformers with BaryCache](https://mlsanity.com/paper/2608.28670/) (2026)

## Abstract (arXiv)

Deep learning based image compression has recently witnessed exciting progress and in some cases even managed to surpass transform coding based approaches that have been established and refined over many decades. However, state-of-the-art solutions for deep image compression typically employ autoencoders which map the input to a lower dimensional latent space and thus irreversibly discard information already before quantization. Due to that, they inherently limit the range of quality levels that can be covered. In contrast, traditional approaches in image compression allow for a larger range of quality levels. Interestingly, they employ an invertible transformation before performing the quantization step which explicitly discards information. Inspired by this, we propose a deep image compression method that is able to go from low bit-rates to near lossless quality by leveraging normalizing flows to learn a bijective mapping from the image space to a latent representation. In addition to this, we demonstrate further advantages unique to our solution, such as the ability to maintain constant quality results through re-encoding, even when performed multiple times. To the best of our knowledge, this is the first work to explore the opportunities for leveraging normalizing flows for lossy image compression.