Saved in:
Bibliographic Details
Main Authors: Ghildyal, Abhijay, Wang, Li-Yun, Liu, Feng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.12668
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909740314918912
author Ghildyal, Abhijay
Wang, Li-Yun
Liu, Feng
author_facet Ghildyal, Abhijay
Wang, Li-Yun
Liu, Feng
contents Wölfflin's five principles offer a structured approach to analyzing stylistic variations for formal analysis. However, no existing metric effectively predicts all five principles in visual art. Computationally evaluating the visual aspects of a painting requires a metric that can interpret key elements such as color, composition, and thematic choices. Recent advancements in vision-language models (VLMs) have demonstrated their ability to evaluate abstract image attributes, making them promising candidates for this task. In this work, we investigate whether CLIP, pre-trained on large-scale data, can understand and predict Wölfflin's principles. Our findings indicate that it does not inherently capture such nuanced stylistic elements. To address this, we fine-tune CLIP on annotated datasets of real art images to predict a score for each principle. We evaluate our model, WP-CLIP, on GAN-generated paintings and the Pandora-18K art dataset, demonstrating its ability to generalize across diverse artistic styles. Our results highlight the potential of VLMs for automated art analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12668
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WP-CLIP: Leveraging CLIP to Predict Wölfflin's Principles in Visual Art
Ghildyal, Abhijay
Wang, Li-Yun
Liu, Feng
Computer Vision and Pattern Recognition
Wölfflin's five principles offer a structured approach to analyzing stylistic variations for formal analysis. However, no existing metric effectively predicts all five principles in visual art. Computationally evaluating the visual aspects of a painting requires a metric that can interpret key elements such as color, composition, and thematic choices. Recent advancements in vision-language models (VLMs) have demonstrated their ability to evaluate abstract image attributes, making them promising candidates for this task. In this work, we investigate whether CLIP, pre-trained on large-scale data, can understand and predict Wölfflin's principles. Our findings indicate that it does not inherently capture such nuanced stylistic elements. To address this, we fine-tune CLIP on annotated datasets of real art images to predict a score for each principle. We evaluate our model, WP-CLIP, on GAN-generated paintings and the Pandora-18K art dataset, demonstrating its ability to generalize across diverse artistic styles. Our results highlight the potential of VLMs for automated art analysis.
title WP-CLIP: Leveraging CLIP to Predict Wölfflin's Principles in Visual Art
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.12668