Large Language Model for Lossless Image Compression with Visual Prompts

TL;DR

This paper presents a novel lossless image compression method that leverages large language models with visual prompts, achieving state-of-the-art results by integrating visual embeddings and residual prediction.

Contribution

Introduces a new paradigm using LLMs with visual prompts for lossless image compression, bridging textual prior knowledge and image data to improve entropy modeling.

Findings

Achieves state-of-the-art compression performance on benchmark datasets.

Effectively extends to medical and screen content images.

Outperforms traditional and existing learning-based codecs.

Abstract

Recent advancements in deep learning have driven significant progress in lossless image compression. With the emergence of Large Language Models (LLMs), preliminary attempts have been made to leverage the extensive prior knowledge embedded in these pretrained models to enhance lossless image compression, particularly by improving the entropy model. However, a significant challenge remains in bridging the gap between the textual prior knowledge within LLMs and lossless image compression. To tackle this challenge and unlock the potential of LLMs, this paper introduces a novel paradigm for lossless image compression that incorporates LLMs with visual prompts. Specifically, we first generate a lossy reconstruction of the input image as visual prompts, from which we extract features to serve as visual embeddings for the LLM. The residual between the original image and the lossy reconstruction is then fed into the LLM along with these visual embeddings, enabling the LLM to function as an entropy model to predict the probability distribution of the residual. Extensive experiments on multiple benchmark datasets demonstrate our method achieves state-of-the-art compression performance, surpassing both traditional and learning-based lossless image codecs. Furthermore, our approach can be easily extended to images from other domains, such as medical and screen content images, achieving impressive performance. These results highlight the potential of LLMs for lossless image compression and may inspire further research in related directions.