# Fidelity-Controllable Extreme Image Compression with Generative Adversarial Networks

arXiv: https://arxiv.org/abs/2008.10314 · HTML: https://mlsanity.com/paper/2008.10314/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Aug 2020.

## Built on by (most cited first, 29 of 29)

- [Multi-Realism Image Compression with a Conditional Generator](https://mlsanity.com/paper/2212.13824/) (2022)
- [Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Prior](https://mlsanity.com/paper/2404.18820/) (2024)
- [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)
- [Extreme Image Compression using Fine-tuned VQGANs](https://mlsanity.com/paper/2307.08265/) (2023)
- [Idempotence and Perceptual Image Compression](https://mlsanity.com/paper/2401.08920/) (2024)
- [On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework](https://mlsanity.com/paper/2106.02782/) (2021)
- [Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression](https://mlsanity.com/paper/2505.16177/) (2025)
- [Generative Latent Coding for Ultra-Low Bitrate Image Compression](https://mlsanity.com/paper/2512.20194/) (2025)
- [EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentation](https://mlsanity.com/paper/2309.03244/) (2023)
- [All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation](https://mlsanity.com/paper/2409.19660/) (2024)
- [Optimally Controllable Perceptual Lossy Compression](https://mlsanity.com/paper/2206.10082/) (2022)
- [Unifying Generation and Compression: Ultra-low bitrate Image Coding Via Multi-stage Transformer](https://mlsanity.com/paper/2403.03736/) (2024)
- [CoD: A Diffusion Foundation Model for Image Compression](https://mlsanity.com/paper/2511.18706/) (2025)
- [High-Fidelity Variable-Rate Image Compression via Invertible Activation Transformation](https://mlsanity.com/paper/2209.05054/) (2022)
- [Conditional Perceptual Quality Preserving Image Compression](https://mlsanity.com/paper/2308.08154/) (2023)
- [LMM-driven Semantic Image-Text Coding for Ultra Low-bitrate Learned Image Compression](https://mlsanity.com/paper/2411.13033/) (2024)
- [SQ-GAN: Semantic Image Communications Using Masked Vector Quantization](https://mlsanity.com/paper/2502.09520/) (2025)
- [Single-step Diffusion for Image Compression at Ultra-Low Bitrates](https://mlsanity.com/paper/2506.16572/) (2025)
- [Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior](https://mlsanity.com/paper/2511.22549/) (2025)
- [Map-Assisted Remote-Sensing Image Compression at Extremely Low Bitrates](https://mlsanity.com/paper/2409.01935/) (2024)
- [Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priors](https://mlsanity.com/paper/2603.15129/) (2026)
- [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)
- [Fast Training-free Perceptual Image Compression](https://mlsanity.com/paper/2506.16102/) (2025)
- [UniMIC: Token-Based Multimodal Interactive Coding for Human-AI Collaboration](https://mlsanity.com/paper/2509.22570/) (2025)
- [Joint Degradation-Aware Arbitrary-Scale Super-Resolution for Variable-Rate Extreme Image Compression](https://mlsanity.com/paper/2603.17408/) (2026)
- [Adaptive Fused Prior Transfer for Controllable Generative Image Compression](https://mlsanity.com/paper/2605.16817/) (2026)
- [Recasting DiT for Extreme Image Compression with Hierarchical Visual Priors](https://mlsanity.com/paper/2610.18607/) (2026)

## Abstract (arXiv)

We propose a GAN-based image compression method working at extremely low bitrates below 0.1bpp. Most existing learned image compression methods suffer from blur at extremely low bitrates. Although GAN can help to reconstruct sharp images, there are two drawbacks. First, GAN makes training unstable. Second, the reconstructions often contain unpleasing noise or artifacts. To address both of the drawbacks, our method adopts two-stage training and network interpolation. The two-stage training is effective to stabilize the training. Moreover, the network interpolation utilizes the models in both stages and reduces undesirable noise and artifacts, while maintaining important edges. Hence, we can control the trade-off between perceptual quality and fidelity without re-training models. The experimental results show that our model can reconstruct high quality images. Furthermore, our user study confirms that our reconstructions are preferable to state-of-the-art GAN-based image compression model. The code will be available.