Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

APDDv2: Aesthetics of Paintings and Drawings Dataset with Artist Labeled Scores and Comments

Xin Jin, Qianqian Qiao, Yi Lu, Huaye Wang, Heng Huang, Shan Gao, Jianfei Liu, Rui Li

TL;DR

The Aesthetics Paintings and Drawings Dataset (APDD) is introduced, the first comprehensive collection of paintings encompassing 24 distinct artistic categories and 10 aesthetic attributes, and an updated version of the Art Assessment Network for Specific Painting Styles, denoted as ArtCLIP.

Abstract

Datasets play a pivotal role in training visual models, facilitating the development of abstract understandings of visual features through diverse image samples and multidimensional attributes. However, in the realm of aesthetic evaluation of artistic images, datasets remain relatively scarce. Existing painting datasets are often characterized by limited scoring dimensions and insufficient annotations, thereby constraining the advancement and application of automatic aesthetic evaluation methods in the domain of painting. To bridge this gap, we introduce the Aesthetics Paintings and Drawings Dataset (APDD), the first comprehensive collection of paintings encompassing 24 distinct artistic categories and 10 aesthetic attributes. Building upon the initial release of APDDv1, our ongoing research has identified opportunities for enhancement in data scale and annotation precision. Consequently, APDDv2 boasts an expanded image corpus and improved annotation quality, featuring detailed language comments to better cater to the needs of both researchers and practitioners seeking high-quality painting datasets. Furthermore, we present an updated version of the Art Assessment Network for Specific Painting Styles, denoted as ArtCLIP. Experimental validation demonstrates the superior performance of this revised model in the realm of aesthetic evaluation, surpassing its predecessor in accuracy and efficacy. The dataset and model are available at https://github.com/BestiVictory/APDDv2.git.

APDDv2: Aesthetics of Paintings and Drawings Dataset with Artist Labeled Scores and Comments

TL;DR

The Aesthetics Paintings and Drawings Dataset (APDD) is introduced, the first comprehensive collection of paintings encompassing 24 distinct artistic categories and 10 aesthetic attributes, and an updated version of the Art Assessment Network for Specific Painting Styles, denoted as ArtCLIP.

Abstract

Datasets play a pivotal role in training visual models, facilitating the development of abstract understandings of visual features through diverse image samples and multidimensional attributes. However, in the realm of aesthetic evaluation of artistic images, datasets remain relatively scarce. Existing painting datasets are often characterized by limited scoring dimensions and insufficient annotations, thereby constraining the advancement and application of automatic aesthetic evaluation methods in the domain of painting. To bridge this gap, we introduce the Aesthetics Paintings and Drawings Dataset (APDD), the first comprehensive collection of paintings encompassing 24 distinct artistic categories and 10 aesthetic attributes. Building upon the initial release of APDDv1, our ongoing research has identified opportunities for enhancement in data scale and annotation precision. Consequently, APDDv2 boasts an expanded image corpus and improved annotation quality, featuring detailed language comments to better cater to the needs of both researchers and practitioners seeking high-quality painting datasets. Furthermore, we present an updated version of the Art Assessment Network for Specific Painting Styles, denoted as ArtCLIP. Experimental validation demonstrates the superior performance of this revised model in the realm of aesthetic evaluation, surpassing its predecessor in accuracy and efficacy. The dataset and model are available at https://github.com/BestiVictory/APDDv2.git.

Paper Structure

This paper contains 12 sections, 9 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Artistic Image Aesthetic Assessment Datasets
  4. Artistic Image Aesthetic Assessment Models
  5. APDDv2
  6. Artistic Categories and Aesthetic Attributes
  7. Labeling Team
  8. Labeling Process
  9. ArtCLIP
  10. Prospects for APDDv2 and ArtCLIP applications
  11. Limitations
  12. Conclusions

Figures (9)

  • Figure 2: The five-layered tasks of IAQA exhibit an overall inverted triangular distribution in terms of corresponding data volume: as the hierarchy ascends, the data volume decreases, accompanied by a decrease in annotation quality.
  • Figure 3: 24 Artistic Categories in the APDD Dataset.
  • Figure 4: Correspondence between artistic categories and aesthetic attributes.
  • Figure 5: Labeling Team Composition.
  • Figure 6: Scoring benchmark table for "Oil Painting - Symbolism - Still Life" category.
  • ...and 4 more figures