Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You Need

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Kecheng, Zhang, Pingping, Liu, Hui, Liu, Jie, Liu, Yibing, Huang, Jiaxin, Wang, Shiqi, Yan, Hong, Li, Haoliang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913583212789760
author Chen, Kecheng
Zhang, Pingping
Liu, Hui
Liu, Jie
Liu, Yibing
Huang, Jiaxin
Wang, Shiqi
Yan, Hong
Li, Haoliang
author_facet Chen, Kecheng
Zhang, Pingping
Liu, Hui
Liu, Jie
Liu, Yibing
Huang, Jiaxin
Wang, Shiqi
Yan, Hong
Li, Haoliang
contents We have recently witnessed that ``Intelligence" and `` Compression" are the two sides of the same coin, where the language large model (LLM) with unprecedented intelligence is a general-purpose lossless compressor for various data modalities. This attribute particularly appeals to the lossless image compression community, given the increasing need to compress high-resolution images in the current streaming media era. Consequently, a spontaneous envision emerges: Can the compression performance of the LLM elevate lossless image compression to new heights? However, our findings indicate that the naive application of LLM-based lossless image compressors suffers from a considerable performance gap compared with existing state-of-the-art (SOTA) codecs on common benchmark datasets. In light of this, we are dedicated to fulfilling the unprecedented intelligence (compression) capacity of the LLM for lossless image compression tasks, thereby bridging the gap between theoretical and practical compression performance. Specifically, we propose P$^{2}$-LLM, a next-pixel prediction-based LLM, which integrates various elaborated insights and methodologies, \textit{e.g.,} pixel-level priors, the in-context ability of LLM, and a pixel-level semantic preservation strategy, to enhance the understanding capacity of pixel sequences for better next-pixel predictions. Extensive experiments on benchmark datasets demonstrate that P$^{2}$-LLM can beat SOTA classical and learned codecs.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12448
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You Need
Chen, Kecheng
Zhang, Pingping
Liu, Hui
Liu, Jie
Liu, Yibing
Huang, Jiaxin
Wang, Shiqi
Yan, Hong
Li, Haoliang
Computer Vision and Pattern Recognition
Image and Video Processing
We have recently witnessed that ``Intelligence" and `` Compression" are the two sides of the same coin, where the language large model (LLM) with unprecedented intelligence is a general-purpose lossless compressor for various data modalities. This attribute particularly appeals to the lossless image compression community, given the increasing need to compress high-resolution images in the current streaming media era. Consequently, a spontaneous envision emerges: Can the compression performance of the LLM elevate lossless image compression to new heights? However, our findings indicate that the naive application of LLM-based lossless image compressors suffers from a considerable performance gap compared with existing state-of-the-art (SOTA) codecs on common benchmark datasets. In light of this, we are dedicated to fulfilling the unprecedented intelligence (compression) capacity of the LLM for lossless image compression tasks, thereby bridging the gap between theoretical and practical compression performance. Specifically, we propose P$^{2}$-LLM, a next-pixel prediction-based LLM, which integrates various elaborated insights and methodologies, \textit{e.g.,} pixel-level priors, the in-context ability of LLM, and a pixel-level semantic preservation strategy, to enhance the understanding capacity of pixel sequences for better next-pixel predictions. Extensive experiments on benchmark datasets demonstrate that P$^{2}$-LLM can beat SOTA classical and learned codecs.
title Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You Need
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2411.12448