Adaptive mixed-scale feature fusion network for blind AI-generated image quality assessment

Zhou, Tianwei, Tan, Songbai, Zhou, Wei, Luo, Yu, Wang, Yuan-Gen and Yue, Guanghui 2024. Adaptive mixed-scale feature fusion network for blind AI-generated image quality assessment. IEEE Transactions on Broadcasting 70 (3) , pp. 833-843. 10.1109/TBC.2024.3391060

Preview

PDF - Accepted Post-Print Version Download (6MB) | Preview

Abstract

With the increasing maturity of the text-to-image and image-to-image generative models, AI-generated images (AGIs) have shown great application potential in advertisement, entertainment, education, social media, etc. Although remarkable advancements have been achieved in generative models, very few efforts have been paid to design relevant quality assessment models. In this paper, we propose a novel blind image quality assessment (IQA) network, named AMFF-Net, for AGIs. AMFF-Net evaluates AGI quality from three dimensions, i.e.“, visual quality”“, authenticity”, and “consistency”. Specifically, inspired by the characteristics of the human visual system and motivated by the observation that “visual quality” and “authenticity” are characterized by both local and global aspects, AMFF-Net scales the image up and down and takes the scaled images and original-sized image as the inputs to obtain multi-scale features. After that, an Adaptive Feature Fusion (AFF) block is used to adaptively fuse the multi-scale features with learnable weights. In addition, considering the correlation between the image and prompt, AMFF-Net compares the semantic features from text encoder and image encoder to evaluate the text-to-image alignment. We carry out extensive experiments on three AGI quality assessment databases, and the experimental results show that our AMFF-Net obtains better performance than nine state-of-the-art blind IQA methods. The results of ablation experiments further demonstrate the effectiveness of the proposed multi-scale input strategy and AFF block.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Institute of Electrical and Electronics Engineers
ISSN:	0018-9316
Date of First Compliant Deposit:	8 May 2024
Date of Acceptance:	27 March 2024
Last Modified:	07 Nov 2024 22:45
URI:	https://orca.cardiff.ac.uk/id/eprint/168783

Actions (repository staff only)

Edit Item