# Exploring the Limits of Semantic Image Compression at Micro-bits per Pixel

arXiv: https://arxiv.org/abs/2402.13536 · HTML: https://mlsanity.com/paper/2402.13536/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 5 references that are in the map.
- First posted on arXiv 21 Feb 2024.

## Builds on (most cited first, 3 of 3)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Text + Sketch: Image Compression at Ultra Low Rates](https://mlsanity.com/paper/2307.01944/) (2023)
- [Semantic Compression With Large Language Models](https://mlsanity.com/paper/2304.12512/) (2023)

## Built on by (most cited first, 2 of 2)

- [Semantic Compression of 3D Objects for Open and Collaborative Virtual Worlds](https://mlsanity.com/paper/2505.16679/) (2025)
- [From Semantic to Token Communication: The Next Paradigm for Large-Model-Driven 6G Intelligent Connectivity](https://mlsanity.com/paper/2609.10714/) (2026)

## Abstract (arXiv)

Traditional methods, such as JPEG, perform image compression by operating on structural information, such as pixel values or frequency content. These methods are effective to bitrates around one bit per pixel (bpp) and higher at standard image sizes. In contrast, text-based semantic compression directly stores concepts and their relationships using natural language, which has evolved with humans to efficiently represent these salient concepts. These methods can operate at extremely low bitrates by disregarding structural information like location, size, and orientation. In this work, we use GPT-4V and DALL-E3 from OpenAI to explore the quality-compression frontier for image compression and identify the limitations of current technology. We push semantic compression as low as 100 μbpp (up to 10,000× smaller than JPEG) by introducing an iterative reflection process to improve the decoded image. We further hypothesize this 100 μbpp level represents a soft limit on semantic compression at standard image resolutions.