LAPIS: A novel dataset for personalized image aesthetic assessment
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913787473297408 |
|---|---|
| author | Maerten, Anne-Sofie Chen, Li-Wei De Winter, Stefanie Bossens, Christophe Wagemans, Johan |
| author_facet | Maerten, Anne-Sofie Chen, Li-Wei De Winter, Stefanie Bossens, Christophe Wagemans, Johan |
| contents | We present the Leuven Art Personalized Image Set (LAPIS), a novel dataset for personalized image aesthetic assessment (PIAA). It is the first dataset with images of artworks that is suitable for PIAA. LAPIS consists of 11,723 images and was meticulously curated in collaboration with art historians. Each image has an aesthetics score and a set of image attributes known to relate to aesthetic appreciation. Besides rich image attributes, LAPIS offers rich personal attributes of each annotator. We implemented two existing state-of-the-art PIAA models and assessed their performance on LAPIS. We assess the contribution of personal attributes and image attributes through ablation studies and find that performance deteriorates when certain personal and image attributes are removed. An analysis of failure cases reveals that both existing models make similar incorrect predictions, highlighting the need for improvements in artistic image aesthetic assessment. The LAPIS project page can be found at: https://github.com/Anne-SofieMaerten/LAPIS |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_07670 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LAPIS: A novel dataset for personalized image aesthetic assessment Maerten, Anne-Sofie Chen, Li-Wei De Winter, Stefanie Bossens, Christophe Wagemans, Johan Computer Vision and Pattern Recognition We present the Leuven Art Personalized Image Set (LAPIS), a novel dataset for personalized image aesthetic assessment (PIAA). It is the first dataset with images of artworks that is suitable for PIAA. LAPIS consists of 11,723 images and was meticulously curated in collaboration with art historians. Each image has an aesthetics score and a set of image attributes known to relate to aesthetic appreciation. Besides rich image attributes, LAPIS offers rich personal attributes of each annotator. We implemented two existing state-of-the-art PIAA models and assessed their performance on LAPIS. We assess the contribution of personal attributes and image attributes through ablation studies and find that performance deteriorates when certain personal and image attributes are removed. An analysis of failure cases reveals that both existing models make similar incorrect predictions, highlighting the need for improvements in artistic image aesthetic assessment. The LAPIS project page can be found at: https://github.com/Anne-SofieMaerten/LAPIS |
| title | LAPIS: A novel dataset for personalized image aesthetic assessment |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.07670 |