# Generative Adversarial Networks for Extreme Learned Image Compression

arXiv: https://arxiv.org/abs/1804.02958 · HTML: https://mlsanity.com/paper/1804.02958/

## Key facts

- Cited by 219 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2018.

## Built on by (most cited first, 30 of 219)

- [Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation](https://mlsanity.com/paper/2310.05737/) (2023)
- [Finite Scalar Quantization: VQ-VAE Made Simple](https://mlsanity.com/paper/2309.15505/) (2023)
- [Checkerboard Context Model for Efficient Learned Image Compression](https://mlsanity.com/paper/2103.15306/) (2021)
- [Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications](https://mlsanity.com/paper/2207.09353/) (2022)
- [Lossy Image Compression with Conditional Diffusion Models](https://mlsanity.com/paper/2209.06950/) (2022)
- [Implicit Neural Representations for Image Compression](https://mlsanity.com/paper/2112.04267/) (2021)
- [FVC: A New Framework towards Deep Video Compression in Feature Space](https://mlsanity.com/paper/2105.09600/) (2021)
- [The Devil Is in the Details: Window-based Attention for Image Compression](https://mlsanity.com/paper/2203.08450/) (2022)
- [Enhanced Invertible Encoding for Learned Image Compression](https://mlsanity.com/paper/2108.03690/) (2021)
- [Towards image compression with perfect realism at ultra-low bitrates](https://mlsanity.com/paper/2310.10325/) (2023)
- [Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models](https://mlsanity.com/paper/2301.11189/) (2023)
- [Semantic Communications: Principles and Challenges](https://mlsanity.com/paper/2201.01389/) (2021)
- [Lossy Compression with Gaussian Diffusion](https://mlsanity.com/paper/2206.08889/) (2022)
- [COIN++: Neural Compression Across Modalities](https://mlsanity.com/paper/2201.12904/) (2022)
- [Multi-Realism Image Compression with a Conditional Generator](https://mlsanity.com/paper/2212.13824/) (2022)
- [An Introduction to Neural Data Compression](https://mlsanity.com/paper/2202.06533/) (2022)
- [ELF-VC: Efficient Learned Flexible-Rate Video Coding](https://mlsanity.com/paper/2104.14335/) (2021)
- [Text + Sketch: Image Compression at Ultra Low Rates](https://mlsanity.com/paper/2307.01944/) (2023)
- [Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Prior](https://mlsanity.com/paper/2404.18820/) (2024)
- [Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform](https://mlsanity.com/paper/2108.09551/) (2021)
- [Generative Joint Source-Channel Coding for Semantic Image Transmission](https://mlsanity.com/paper/2211.13772/) (2022)
- [AdvDrop: Adversarial Attack to DNNs by Dropping Information](https://mlsanity.com/paper/2108.09034/) (2021)
- [High-Fidelity Image Compression with Score-based Generative Models](https://mlsanity.com/paper/2305.18231/) (2023)
- [Lossy Compression for Lossless Prediction](https://mlsanity.com/paper/2106.10800/) (2021)
- [Universal Rate-Distortion-Perception Representations for Lossy Compression](https://mlsanity.com/paper/2106.10311/) (2021)
- [Perceptual Learned Video Compression with Recurrent Conditional GAN](https://mlsanity.com/paper/2109.03082/) (2021)
- [Generative Semantic Communication: Diffusion Models Beyond Bit Recovery](https://mlsanity.com/paper/2306.04321/) (2023)
- [Slimmable Compressive Autoencoders for Practical Neural Image Compression](https://mlsanity.com/paper/2103.15726/) (2021)
- [Neural Video Compression using GANs for Detail Synthesis and Propagation](https://mlsanity.com/paper/2107.12038/) (2021)
- [Towards Semantic Communications: Deep Learning-Based Image Semantic Coding](https://mlsanity.com/paper/2208.04094/) (2022)

## Abstract (arXiv)

We present a learned image compression system based on GANs, operating at extremely low bitrates. Our proposed framework combines an encoder, decoder/generator and a multi-scale discriminator, which we train jointly for a generative learned compression objective. The model synthesizes details it cannot afford to store, obtaining visually pleasing results at bitrates where previous methods fail and show strong artifacts. Furthermore, if a semantic label map of the original image is available, our method can fully synthesize unimportant regions in the decoded image such as streets and trees from the label map, proportionally reducing the storage cost. A user study confirms that for low bitrates, our approach is preferred to state-of-the-art methods, even when they use more than double the bits.