With the rapid advancement of artificial intelligence, the field of Artificial Intelligence Generated Content (AIGC) has seen significant growth. As AI-generated images (AIGIs) become increasingly prevalent, the AIGC image quality assessment(AIGCIQA) has gained critical importance. However, traditional image quality assessment methods struggle to account for the complex relationship between generated images and their corresponding text prompts, leading to suboptimal performance in AIGCIQA tasks. Additionally, the scarcity of subjective annotation data within AIGCIQA datasets limits the effectiveness of deep learning models. To address these challenges, we propose a novel self-supervised task that utilizes intermediate image sequences generated during Text-to-Image (T2I) model generation as the pre-training data. We use the number of model iterations as pseudo-labels based on the positive correlation between image quality and the number of model iterations. Due to the relative coarseness of this pseudo-label as a supervised signal, we also introduce a linear interpolation method for optimization. Additionally, we designed a framework that effectively fuses image and text features. The framework considers the dynamic fading properties of intermediate image sequences similar to video clips. It utilizes a specialized text prompt template and extracts image features through a cross-attention mechanism, which significantly improves model performance. Experimental results show that the proposed method achieves state-of-the-art performance on three mainstream AIGCIQA datasets.

In recent years, deep learning-based methods have made significant progress on the image quality assessment problem; however, challenges remain arising from the lack of annotated, real-world training data and consequent poor generalization ability. Towards addressing these challenges, we propose a no-reference image quality assessment (NR-IQA) method based on generative AI (GenAI) images. Specifically, we use GenAI images as reference images, employing a cold diffusion model to generate distorted images of four different distortion types, and we label these distorted images using a full-reference model, thereby making it possible to construct a large-scale pre-training dataset. We use this resource generation method to facilitate NR-IQA model building. We deploy a Multi-scale Cross Attention Block (MCAB) and a Scale Simple Attention Module (SSAM) to enhance feature representation by extracting multi-scale feature information from both the channel and spatial dimensions that are predictive of image quality. Extensive experiments on eight public databases demonstrate that the proposed method achieves state-of-the-art (SOTA) performance. A public release of all the codes associated with this work will be made available on GitHub.

Most currently developed video quality assessment (VQA) algorithms have achieved excellent performance by using deep neural network (DNN). However, DNN is vulnerable to adversarial attacks , as an efficient surrogate for validating the model robustness, and there lack adversarial attack methods against VQA models. To this end, we propose a spatiotemporal attack network to generate adversarial examples for evaluating the robustness of VQA models that contains a spatial subnetwork and a temporal subnetwork . The proposed network, dubbed the Space-Time Quality Attack Network (STQA-Net 1 ), first computes the just noticeable difference (JND) maps of a video sequence as the input of the spatial subnetwork. The spatial subnetwork encodes the computed maps as spatial features and feeds the spatial features to the temporal subnetwork. Then, the spatial features are fused with the output of the temporal subnetwork and the fused features are decoded as attack weight maps. A visual constraint is used to control the visibility of perturbations and guide the generation of perturbation maps by multiplying JND maps with attack weight maps. Finally, the generated perturbation maps are added to the original video to form an adversarial example. Further, we also try to design a two-branch network to generate two opposite examples in a targeted attack scenario. The proposed attack methods against six state-of-the-art VQA algorithms are thoroughly tested on three VQA databases. The experimental results show that the proposed attack methods are very effective for testing the robustness of VQA models.

Abstract With the development of mobile phone camera technology, mobile phones can take a large number of macro photography images that previously could only be taken by professional cameras. Therefore, it is of great significance to study the quality of macro photography images. For this reason, a macro photography image visual quality evaluation database is established and it is named as MP2020. The database contains 100 reference images and 800 distorted images of four distortion types, including 200 distorted images of JPEG 2000, 200 distorted images of JPEG, 200 distorted images of white noise, and 200 distorted images of Gaussian blur. The DMOS values in the database were calculated from 48000 data which are provided by 60 subjects. Ten classical image quality assessment algorithms were tested on the MP2020 database. The experimental results show that the existing image quality assessment algorithms, which are widely used, are not applicable to the macro photography images. Therefore, MP2020 would contribute to the improvement of existing algorithms and the development of new algorithms. MP2020 has been uploaded to GitHub for download.