Bringing Textual Prompt to AI-Generated Image Quality Assessment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qu, Bowen, Li, Haohui, Gao, Wei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916253648551936
author Qu, Bowen
Li, Haohui
Gao, Wei
author_facet Qu, Bowen
Li, Haohui
Gao, Wei
contents AI-Generated Images (AGIs) have inherent multimodal nature. Unlike traditional image quality assessment (IQA) on natural scenarios, AGIs quality assessment (AGIQA) takes the correspondence of image and its textual prompt into consideration. This is coupled in the ground truth score, which confuses the unimodal IQA methods. To solve this problem, we introduce IP-IQA (AGIs Quality Assessment via Image and Prompt), a multimodal framework for AGIQA via corresponding image and prompt incorporation. Specifically, we propose a novel incremental pretraining task named Image2Prompt for better understanding of AGIs and their corresponding textual prompts. An effective and efficient image-prompt fusion module, along with a novel special [QA] token, are also applied. Both are plug-and-play and beneficial for the cooperation of image and its corresponding prompt. Experiments demonstrate that our IP-IQA achieves the state-of-the-art on AGIQA-1k and AGIQA-3k datasets. Code will be available at https://github.com/Coobiw/IP-IQA.
format Preprint
id arxiv_https___arxiv_org_abs_2403_18714
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bringing Textual Prompt to AI-Generated Image Quality Assessment
Qu, Bowen
Li, Haohui
Gao, Wei
Computer Vision and Pattern Recognition
Multimedia
AI-Generated Images (AGIs) have inherent multimodal nature. Unlike traditional image quality assessment (IQA) on natural scenarios, AGIs quality assessment (AGIQA) takes the correspondence of image and its textual prompt into consideration. This is coupled in the ground truth score, which confuses the unimodal IQA methods. To solve this problem, we introduce IP-IQA (AGIs Quality Assessment via Image and Prompt), a multimodal framework for AGIQA via corresponding image and prompt incorporation. Specifically, we propose a novel incremental pretraining task named Image2Prompt for better understanding of AGIs and their corresponding textual prompts. An effective and efficient image-prompt fusion module, along with a novel special [QA] token, are also applied. Both are plug-and-play and beneficial for the cooperation of image and its corresponding prompt. Experiments demonstrate that our IP-IQA achieves the state-of-the-art on AGIQA-1k and AGIQA-3k datasets. Code will be available at https://github.com/Coobiw/IP-IQA.
title Bringing Textual Prompt to AI-Generated Image Quality Assessment
topic Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2403.18714