ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916889543835648 |
|---|---|
| author | Cao, Shuo Ma, Nan Li, Jiayang Li, Xiaohui Shao, Lihao Zhu, Kaiwen Zhou, Yu Pu, Yuandong Wu, Jiarui Wang, Jiaquan Qu, Bo Wang, Wenhai Qiao, Yu Yao, Dajuin Liu, Yihao |
| author_facet | Cao, Shuo Ma, Nan Li, Jiayang Li, Xiaohui Shao, Lihao Zhu, Kaiwen Zhou, Yu Pu, Yuandong Wu, Jiarui Wang, Jiaquan Qu, Bo Wang, Wenhai Qiao, Yu Yao, Dajuin Liu, Yihao |
| contents | The rapid advancement of educational applications, artistic creation, and AI-generated content (AIGC) technologies has substantially increased practical requirements for comprehensive Image Aesthetics Assessment (IAA), particularly demanding methods capable of delivering both quantitative scoring and professional understanding. Multimodal Large Language Model (MLLM)-based IAA methods demonstrate stronger perceptual and generalization capabilities compared to traditional approaches, yet they suffer from modality bias (score-only or text-only) and lack fine-grained attribute decomposition, thereby failing to support further aesthetic assessment. In this paper, we present:(1) ArtiMuse, an innovative MLLM-based IAA model with Joint Scoring and Expert-Level Understanding capabilities; (2) ArtiMuse-10K, the first expert-curated image aesthetic dataset comprising 10,000 images spanning 5 main categories and 15 subcategories, each annotated by professional experts with 8-dimensional attributes analysis and a holistic score. Both the model and dataset will be made public to advance the field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_14533 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding Cao, Shuo Ma, Nan Li, Jiayang Li, Xiaohui Shao, Lihao Zhu, Kaiwen Zhou, Yu Pu, Yuandong Wu, Jiarui Wang, Jiaquan Qu, Bo Wang, Wenhai Qiao, Yu Yao, Dajuin Liu, Yihao Computer Vision and Pattern Recognition The rapid advancement of educational applications, artistic creation, and AI-generated content (AIGC) technologies has substantially increased practical requirements for comprehensive Image Aesthetics Assessment (IAA), particularly demanding methods capable of delivering both quantitative scoring and professional understanding. Multimodal Large Language Model (MLLM)-based IAA methods demonstrate stronger perceptual and generalization capabilities compared to traditional approaches, yet they suffer from modality bias (score-only or text-only) and lack fine-grained attribute decomposition, thereby failing to support further aesthetic assessment. In this paper, we present:(1) ArtiMuse, an innovative MLLM-based IAA model with Joint Scoring and Expert-Level Understanding capabilities; (2) ArtiMuse-10K, the first expert-curated image aesthetic dataset comprising 10,000 images spanning 5 main categories and 15 subcategories, each annotated by professional experts with 8-dimensional attributes analysis and a holistic score. Both the model and dataset will be made public to advance the field. |
| title | ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.14533 |