# CompressNet: Generative Compression at Extremely Low Bitrates

arXiv: https://arxiv.org/abs/2006.08003 · HTML: https://mlsanity.com/paper/2006.08003/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2020.

## Built on by (most cited first, 10 of 10)

- [Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Prior](https://mlsanity.com/paper/2404.18820/) (2024)
- [Extreme Generative Image Compression by Learning Text Embedding from Diffusion Models](https://mlsanity.com/paper/2211.07793/) (2022)
- [Learning-Driven Lossy Image Compression; A Comprehensive Survey](https://mlsanity.com/paper/2201.09240/) (2022)
- [Content-oriented learned image compression](https://mlsanity.com/paper/2207.14168/) (2022)
- [Compressing Sensor Data for Remote Assistance of Autonomous Vehicles using Deep Generative Models](https://mlsanity.com/paper/2111.03201/) (2021)
- [Single-step Diffusion for Image Compression at Ultra-Low Bitrates](https://mlsanity.com/paper/2506.16572/) (2025)
- [You Can Mask More For Extremely Low-Bitrate Image Compression](https://mlsanity.com/paper/2306.15561/) (2023)
- [Map-Assisted Remote-Sensing Image Compression at Extremely Low Bitrates](https://mlsanity.com/paper/2409.01935/) (2024)
- [SDGIC: A Semantic Disambiguation-Guided Generative Image Compression Method for Ultra-Low Bitrates](https://mlsanity.com/paper/2512.06344/) (2025)
- [Joint Degradation-Aware Arbitrary-Scale Super-Resolution for Variable-Rate Extreme Image Compression](https://mlsanity.com/paper/2603.17408/) (2026)

## Abstract (arXiv)

Compressing images at extremely low bitrates (< 0.1 bpp) has always been a challenging task since the quality of reconstruction significantly reduces due to the strong imposed constraint on the number of bits allocated for the compressed data. With the increasing need to transfer large amounts of images with limited bandwidth, compressing images to very low sizes is a crucial task. However, the existing methods are not effective at extremely low bitrates. To address this need, we propose a novel network called CompressNet which augments a Stacked Autoencoder with a Switch Prediction Network (SAE-SPN). This helps in the reconstruction of visually pleasing images at these low bitrates (< 0.1 bpp). We benchmark the performance of our proposed method on the Cityscapes dataset, evaluating over different metrics at extremely low bitrates to show that our method outperforms the other state-of-the-art. In particular, at a bitrate of 0.07, CompressNet achieves 22% lower Perceptual Loss and 55% lower Frechet Inception Distance (FID) compared to the deep learning SOTA methods.