Saved in:
Bibliographic Details
Main Authors: Dotzel, Jordan, Kotb, Bahaa, Dotzel, James, Abdelfattah, Mohamed, Zhang, Zhiru
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.13536
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913238466166784
author Dotzel, Jordan
Kotb, Bahaa
Dotzel, James
Abdelfattah, Mohamed
Zhang, Zhiru
author_facet Dotzel, Jordan
Kotb, Bahaa
Dotzel, James
Abdelfattah, Mohamed
Zhang, Zhiru
contents 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 $μ$bpp (up to $10,000\times$ smaller than JPEG) by introducing an iterative reflection process to improve the decoded image. We further hypothesize this 100 $μ$bpp level represents a soft limit on semantic compression at standard image resolutions.
format Preprint
id arxiv_https___arxiv_org_abs_2402_13536
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring the Limits of Semantic Image Compression at Micro-bits per Pixel
Dotzel, Jordan
Kotb, Bahaa
Dotzel, James
Abdelfattah, Mohamed
Zhang, Zhiru
Computer Vision and Pattern Recognition
Artificial Intelligence
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 $μ$bpp (up to $10,000\times$ smaller than JPEG) by introducing an iterative reflection process to improve the decoded image. We further hypothesize this 100 $μ$bpp level represents a soft limit on semantic compression at standard image resolutions.
title Exploring the Limits of Semantic Image Compression at Micro-bits per Pixel
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2402.13536