AIGCIQA2023: A Large-scale Image Quality Assessment Database for AI Generated Images: from the Perspectives of Quality, Authenticity and Correspondence

Jiarui Wang, Huiyu Duan, Jing Liu, Shi Chen, Xiongkuo Min +1 more
7/1/2023
cs.CVeess.IV

No official code found. Best implementation: wangjiarui153/AIGCIQA2023 (28 stars, last commit 2025-05-23).

Abstract

In this paper, in order to get a better understanding of the human visual preferences for AIGIs, a large-scale IQA database for AIGC is established, which is named as AIGCIQA2023. We first generate over 2000 images based on 6 state-of-the-art text-to-image generation models using 100 prompts. Based on these images, a well-organized subjective experiment is conducted to assess the human visual preferences for each image from three perspectives including quality, authenticity and correspondence. Finally, based on this large-scale database, we conduct a benchmark experiment to evaluate the performance of several state-of-the-art IQA metrics on our constructed database.

View on arXivView PDF

Code Implementations(1)

wangjiarui153/AIGCIQA2023Community100%
281Jul 1, 20231 years ago

Similar Papers

Quality Assessment for AI Generated Images with Instruction Tuning

89% match1 repo212024

Learning Multi-Dimensional Human Preference for Text-to-Image Generation

87% match1 repo4262024

Image Intrinsic Scale Assessment: Bridging the Gap Between Quality and Resolution

87% match1 repo172025

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

87% match2 repos702024

3DGen-Bench: Comprehensive Benchmark Suite for 3D Generative Models

86% match2025

Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation

86% match1 repo6052023

Cite this paper

@article{wang2023aigciqa,
  title  = {AIGCIQA2023: A Large-scale Image Quality Assessment Database for AI Generated Images: from the Perspectives of Quality, Authenticity and Correspondence},
  author = {Jiarui Wang and Huiyu Duan and Jing Liu and Shi Chen and Xiongkuo Min and Guangtao Zhai},
  year   = {2023},
  eprint = {2307.00211},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.00211v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.00211.svg)](https://codeofpaper.com/paper/2307.00211)

Discussion