Subjective Quality

Subjective quality assessment aims to quantify human perception of quality in various media, such as images, videos, and audio, bridging the gap between objective metrics and user experience. Current research focuses on developing robust models, often employing deep learning architectures like convolutional neural networks and transformers, to predict subjective quality scores from diverse features, including temporal distortions and multi-dimensional quality aspects. This work is crucial for improving the quality of AI-generated content, optimizing compression techniques, and developing more accurate and efficient quality assessment tools across various multimedia applications. The creation of large-scale, subjectively annotated datasets is a key driver of progress in this field.