QUASAR: QUality and Aesthetics Scoring with Advanced Representations

arXiv:2403.06866v1 Announce Type: new
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 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 …

abstract advanced anchors art arxiv assessment cs.cv data data-driven embeddings engineering fine-tuning image non-parametric paper parametric prompt quality scoring state textual through type