QUASAR: QUality and Aesthetics Scoring with Advanced Representations
This provides a streamlined solution for image assessment, benefiting applications in computer vision and media, though it appears incremental as it builds on self-supervised models.
The paper tackles image quality and aesthetics assessment by introducing a data-driven, non-parametric method that surpasses existing approaches, achieving high agreement with human assessments and robustness across datasets without requiring prompt engineering or fine-tuning.
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 7 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.