A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
The ArtBench Dataset: Benchmarking Generative Models with Artworks
[article]
2022
arXiv
pre-print
Preserved Fulltext
We introduce ArtBench-10, the first class-balanced, high-quality, cleanly annotated, and standardized dataset for benchmarking artwork generation. ...
We also conduct extensive benchmarking experiments using representative image synthesis models with ArtBench-10 and present in-depth analysis. ...
The authors would also like to express gratitude towards WikiArt, the Surrealism Website, Japanese Woodblock Print Search, and all the artists who appeared in the dataset. ...
arXiv:2206.11404v1
fatcat:6ci5o75ttnglff4gab5bczi6la