# Understanding and Creating Art with AI: Review and Outlook

**Authors:** Eva Cetinic, James She  
**arXiv:** [2102.09109](https://arxiv.org/abs/2102.09109)  
**Date:** 2021-02-18  
**Summary page:** https://www.summarizepaper.com/en/paper/2102.09109v1/

## Key points

- The intersection of AI and art is transforming the way we understand and create visual arts.
- The paper titled "Understanding and Creating Art with AI: Review and Outlook" provides an integrated review of two facets of AI in art:
- Using AI for art analysis on digitized artwork collections
- Using AI for creative purposes to generate novel artworks
- The authors present a comprehensive overview of various artwork datasets and recent works that address tasks such as classification, object detection, similarity retrieval, multimodal representations, computational aesthetics, among others.
- They also delve into the practical and theoretical aspects of AI Art creation, consolidating related works that deal with those topics in detail.
- The paper provides insights into the future progression and potential impact of AI technologies on our understanding and creation of art.
- The authors highlight how these technologies have already transformed research practices in visual arts by enabling new ways to analyze large collections of digitized artworks.
- They also discuss how AI is being used to generate novel artworks autonomously or collaboratively with human artists.

## Summary

The intersection of artificial intelligence (AI) and art has led to a growing number of research initiatives and creative applications that are transforming the way we understand and create visual arts. In this paper titled "Understanding and Creating Art with AI: Review and Outlook," Eva Cetinic and James She provide an integrated review of two facets of AI in art: 1) using AI for art analysis on digitized artwork collections, and 2) using AI for creative purposes to generate novel artworks. The authors present a comprehensive overview of various artwork datasets and recent works that address tasks such as classification, object detection, similarity retrieval, multimodal representations, computational aesthetics, among others. They also delve into the practical and theoretical aspects of AI Art creation, consolidating related works that deal with those topics in detail. The paper provides insights into the future progression and potential impact of AI technologies on our understanding and creation of art. The authors highlight how these technologies have already transformed research practices in visual arts by enabling new ways to analyze large collections of digitized artworks. They also discuss how AI is being used to generate novel artworks autonomously or collaboratively with human artists. Overall, this paper offers a valuable contribution to the ongoing discourse on the role of AI in art by providing a comprehensive review of current research initiatives while offering insights into future possibilities.