AI-generated Image Quality Assessment in Visual Communication

I tiakina i:

Ngā taipitopito rārangi puna kōrero
I whakaputaina i:	arXiv.org (Dec 20, 2024), p. n/a
Kaituhi matua:	Tian, Yu
Ētahi atu kaituhi:	Li, Yixuan, Chen, Baoliang, Zhu, Hanwei, Wang, Shiqi, Kwong, Sam
I whakaputaina:	Cornell University Library, arXiv.org
Ngā marau:	Visual fields Quality assessment Datasets Annotations Image quality Visual perception Artificial intelligence Visual perception driven algorithms
Urunga tuihono:	Citation/Abstract Full text outside of ProQuest
Ngā Tūtohu:	Tāpirihia he Tūtohu Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!

Whakaahuatanga
Whakarāpopotonga:	Assessing the quality of artificial intelligence-generated images (AIGIs) plays a crucial role in their application in real-world scenarios. However, traditional image quality assessment (IQA) algorithms primarily focus on low-level visual perception, while existing IQA works on AIGIs overemphasize the generated content itself, neglecting its effectiveness in real-world applications. To bridge this gap, we propose AIGI-VC, a quality assessment database for AI-Generated Images in Visual Communication, which studies the communicability of AIGIs in the advertising field from the perspectives of information clarity and emotional interaction. The dataset consists of 2,500 images spanning 14 advertisement topics and 8 emotion types. It provides coarse-grained human preference annotations and fine-grained preference descriptions, benchmarking the abilities of IQA methods in preference prediction, interpretation, and reasoning. We conduct an empirical study of existing representative IQA methods and large multi-modal models on the AIGI-VC dataset, uncovering their strengths and weaknesses.
ISSN:	2331-8422
Puna:	Engineering Database