AIGIQA-20K: A Large Database for AI-Generated Image Quality Assessment

Chunyi Li,Tengchuan Kou,Yixuan Gao,Yuqin Cao,Wei Sun,Zicheng Zhang,Yingjie Zhou, Zhichao Zhang,Weixia Zhang,Haoning Wu,Xiaohong Liu,Xiongkuo Min,Guangtao ZhaiTop Scholar

Computing Research Repository (CoRR)（2024）

Nanyang Technological University

Cited 21|Views64

Abstract

With the rapid advancements in AI-Generated Content (AIGC), AI-GeneratedImages (AIGIs) have been widely applied in entertainment, education, and socialmedia. However, due to the significant variance in quality among differentAIGIs, there is an urgent need for models that consistently match humansubjective ratings. To address this issue, we organized a challenge towardsAIGC quality assessment on NTIRE 2024 that extensively considers 15 populargenerative models, utilizing dynamic hyper-parameters (includingclassifier-free guidance, iteration epochs, and output image resolution), andgather subjective scores that consider perceptual quality and text-to-imagealignment altogether comprehensively involving 21 subjects. This approachculminates in the creation of the largest fine-grained AIGI subjective qualitydatabase to date with 20,000 AIGIs and 420,000 subjective ratings, known asAIGIQA-20K. Furthermore, we conduct benchmark experiments on this database toassess the correspondence between 16 mainstream AIGI quality models and humanperception. We anticipate that this large-scale quality database will inspirerobust quality indicators for AIGIs and propel the evolution of AIGC forvision. The database is released onhttps://www.modelscope.cn/datasets/lcysyzxdxc/AIGCQA-30K-Image.

Translated text

Key words

AI-Generated Content,Image Quality Assessment

Bibtex

AI Read Science

AI Summary

AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.

Example

Background

Key content

Introduction

Methods

Results

Related work

Fund

Key content

Pretraining has recently greatly promoted the development of natural language processing (NLP)
We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance

Try using models to generate summary,it takes about 60s

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper