Image Quality Assessment
Image Quality Assessment (IQA) aims to objectively measure the perceived quality of images, often by correlating automated metrics with human judgments. Current research focuses on developing robust, training-efficient methods, particularly for no-reference IQA (NR-IQA), employing architectures like transformers and convolutional neural networks, often incorporating techniques like contrastive learning and vision-language models. These advancements are crucial for various applications, including image processing, medical imaging, and the evaluation of AI-generated content, improving the reliability and efficiency of computer vision systems.
Papers
Beyond MOS: Subjective Image Quality Score Preprocessing Method Based on Perceptual Similarity
Lei Wang, Desen Yuan
Perceptual Constancy Constrained Single Opinion Score Calibration for Image Quality Assessment
Lei Wang, Desen Yuan
Causal Perception Inspired Representation Learning for Trustworthy Image Quality Assessment
Lei Wang, Desen Yuan
Adaptive Mixed-Scale Feature Fusion Network for Blind AI-Generated Image Quality Assessment
Tianwei Zhou, Songbai Tan, Wei Zhou, Yu Luo, Yuan-Gen Wang, Guanghui Yue
Multi-Modal Prompt Learning on Blind Image Quality Assessment
Wensheng Pan, Timin Gao, Yan Zhang, Runze Hu, Xiawu Zheng, Enwei Zhang, Yuting Gao, Yutao Liu, Yunhang Shen, Ke Li, Shengchuan Zhang, Liujuan Cao, Rongrong Ji