Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.06866 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913272908742656 |
|---|---|
| author | Kastryulin, Sergey Prokopenko, Denis Babenko, Artem Dylov, Dmitry V. |
| author_facet | Kastryulin, Sergey Prokopenko, Denis Babenko, Artem Dylov, Dmitry V. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_06866 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | QUASAR: QUality and Aesthetics Scoring with Advanced Representations Kastryulin, Sergey Prokopenko, Denis Babenko, Artem Dylov, Dmitry V. Computer Vision and Pattern Recognition 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. |
| title | QUASAR: QUality and Aesthetics Scoring with Advanced Representations |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.06866 |