Unpaired Cezanne Art and Photographic Image Collection

Encompassing unpaired images of paintings in the style of Paul Cezanne and photographs. It is part of the CycleGAN datasets collection for image-to-image translation research, originally published by researchers at UC Berkeley.

Use Cases

• Train CycleGAN models for unpaired image-to-image translation between Cezanne-style paintings and photographs.
• Evaluate style transfer algorithms using the distinct artistic and photographic domains.
• Use as a benchmark dataset for generative adversarial network research on artistic style transfer.

Strengths

• Part of the established and widely cited CycleGAN datasets collection.
• Designed for a specific, well-defined research task in computer vision.
• Associated with a foundational research paper (arXiv:1703.10593) in the field.

Limitations

• The specific number of images, resolution, and file formats are not detailed in the provided input.
• Limited to the specific artistic style of Cezanne and a corresponding photographic domain.
• Dataset structure and preprocessing details are not specified.

Provenance

Source

Originally hosted by researchers at UC Berkeley's EECS department.

Collection Method

Curated collection of images for unpaired image-to-image translation experiments.

Freshness

Last updated on the platform in April 2022.