QUASAR: QUality and Aesthetics Scoring With Advanced Representations

Abstract

This paper introduces a new data-driven, non-parametric method for image quality and aesthetics assessment, surpassing existing approaches and requiring no prompt engineering or fine-tuning. We eliminate the need for expressive textual embeddings by proposing efficient image anchors in the data. Through extensive evaluations of seven state-of-the-art self-supervised models, our method demonstrates superior performance and robustness across various datasets and benchmarks. Notably, it achieves high agreement with human assessments even with limited data and shows high robustness to the nature of data and their pre-processing pipeline. Our contributions offer a streamlined solution for assessment of images while providing insights into the perception of visual information. The source code of our method can be found at https://github.com/photosynthesis-team/QUASAR.

Keywords

• Foundation models
• image quality assessment
• metrics and benchmarks
• multi-modal representations
• self-supervised learning