# A GAN-based Tunable Image Compression System

arXiv: https://arxiv.org/abs/2001.06580 · HTML: https://mlsanity.com/paper/2001.06580/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jan 2020.

## Built on by (most cited first, 14 of 14)

- [Semantic Communications: Principles and Challenges](https://mlsanity.com/paper/2201.01389/) (2021)
- [High-Fidelity Image Compression with Score-based Generative Models](https://mlsanity.com/paper/2305.18231/) (2023)
- [A Residual Diffusion Model for High Perceptual Quality Codec Augmentation](https://mlsanity.com/paper/2301.05489/) (2023)
- [Extreme Generative Image Compression by Learning Text Embedding from Diffusion Models](https://mlsanity.com/paper/2211.07793/) (2022)
- [On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework](https://mlsanity.com/paper/2106.02782/) (2021)
- [Learning-Driven Lossy Image Compression; A Comprehensive Survey](https://mlsanity.com/paper/2201.09240/) (2022)
- [Optimally Controllable Perceptual Lossy Compression](https://mlsanity.com/paper/2206.10082/) (2022)
- [MobileNVC: Real-time 1080p Neural Video Compression on a Mobile Device](https://mlsanity.com/paper/2310.01258/) (2023)
- [High-Fidelity Variable-Rate Image Compression via Invertible Activation Transformation](https://mlsanity.com/paper/2209.05054/) (2022)
- [Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior](https://mlsanity.com/paper/2511.22549/) (2025)
- [Generative Adversarial Networks for Spatio-Spectral Compression of Hyperspectral Images](https://mlsanity.com/paper/2305.08514/) (2023)
- [GAN-based Image Compression with Improved RDO Process](https://mlsanity.com/paper/2306.10461/) (2023)
- [TACTIC: Joint Rate-Distortion-Accuracy Optimisation for Low Bitrate Compression](https://mlsanity.com/paper/2109.10658/) (2021)
- [Semantic-assisted image compression](https://mlsanity.com/paper/2201.12599/) (2022)

## Abstract (arXiv)

The method of importance map has been widely adopted in DNN-based lossy image compression to achieve bit allocation according to the importance of image contents. However, insufficient allocation of bits in non-important regions often leads to severe distortion at low bpp (bits per pixel), which hampers the development of efficient content-weighted image compression systems. This paper rethinks content-based compression by using Generative Adversarial Network (GAN) to reconstruct the non-important regions. Moreover, multiscale pyramid decomposition is applied to both the encoder and the discriminator to achieve global compression of high-resolution images. A tunable compression scheme is also proposed in this paper to compress an image to any specific compression ratio without retraining the model. The experimental results show that our proposed method improves MS-SSIM by more than 10.3% compared to the recently reported GAN-based method to achieve the same low bpp (0.05) on the Kodak dataset.