Defending No-Reference Image Quality Metrics Against Adversarial Attacks Through Purification Methods
Adversarial attacks can significantly degrade the performance of no-reference image quality assessment metrics. This study investigates the effectiveness of various adversarial purification methods in defending against such attacks and restoring the original metric scores.
A Unified Framework for Full-Reference and No-Reference Image Quality Assessment
The proposed YOTO network can effectively perform both full-reference (FR) and no-reference (NR) image quality assessment tasks using a single unified architecture, outperforming existing task-specific models.
Assessing Human Preferences for AI-Generated Omnidirectional Images: A Comprehensive Database and Benchmark
This study establishes a large-scale database, AIGCOIQA2024, to assess human visual preferences for AI-generated omnidirectional images from the perspectives of quality, comfortability, and correspondence. The database is used to analyze human preference characteristics and conduct a benchmark experiment evaluating state-of-the-art IQA models.
PromptIQA: Boosting Image Quality Assessment via Prompts
PromptIQA directly adapts to new requirements without fine-tuning, outperforming SOTA methods.
Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization
Improving the adversarial robustness of No-Reference Image Quality Assessment models through gradient norm regularization.
Quality-Aware Image-Text Alignment for Real-World Image Quality Assessment
QualiCLIP proposes a quality-aware image-text alignment strategy to enhance CLIP's ability to generate accurate quality-aware image representations.
PICNIQ: Pairwise Comparisons for Image Quality Assessment
Introducing PICNIQ, a novel pairwise comparison framework for image quality assessment that addresses domain shift and uncertainty challenges in BIQA.
Comparison of No-Reference Image Quality Models via MAP Estimation in Diffusion Latents
Contemporary NR-IQA models can be compared using MAP estimation in diffusion latents, providing insights into their relative strengths and weaknesses in perceptual optimization.
