# Rethinking Image Compression on the Web with Generative AI

arXiv: https://arxiv.org/abs/2407.04542 · HTML: https://mlsanity.com/paper/2407.04542/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 16 references that are in the map.
- First posted on arXiv 5 Jul 2024.

## Builds on (most cited first, 5 of 5)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024)
- [OpenELM: An Efficient Language Model Family with Open Training and Inference Framework](https://mlsanity.com/paper/2404.14619/) (2024)

## Built on by (most cited first, 1 of 1)

- [PixLift: Accelerating Web Browsing via AI Upscaling](https://mlsanity.com/paper/2502.08995/) (2025)

## Abstract (arXiv)

The rapid growth of the Internet, driven by social media, web browsing, and video streaming, has made images central to the Web experience, resulting in significant data transfer and increased webpage sizes. Traditional image compression methods, while reducing bandwidth, often degrade image quality. This paper explores a novel approach using generative AI to reconstruct images at the edge or client-side. We develop a framework that leverages text prompts and provides additional conditioning inputs like Canny edges and color palettes to a text-to-image model, achieving up to 99.8% bandwidth savings in the best cases and 92.6% on average, while maintaining high perceptual similarity. Empirical analysis and a user study show that our method preserves image meaning and structure more effectively than traditional compression methods, offering a promising solution for reducing bandwidth usage and improving Internet affordability with minimal degradation in image quality.