Cimg New York Construction - Picasso Seated Nude, "Controlling Perceptual Factors in Neural Style Transfer", Unpublished
Still, 2016
Buy Now $8000
View full-resolution artwork ↗Loading auction…
About the artwork
I spent most of 2016 refining and iterating on the Neural Style Transfer algorithm. Together with collaborators in Tuebingen and during an internship at Adobe in Seattle, we developed methods for high resolution style transfer, for preserving the the color map of the content image and for the controlled application and mixing of styles across image location and scale.
During that time I would generate series of multiple styles applied to multiple content images with and without preservation of colors. Some of these images are preserved and presented below.
Academically, we presented those techniques and some of these images at the CVPR conference in 2017.
Leon Gatys is an AI researcher whose work centers on leveraging data-driven technology to improve human lives. He is currently based in Seattle, Washington, where he supports Apple’s Responsible AI team. Previously, he co-founded PreemptiveAI, a company dedicated to developing foundation models for human health and physiology using data collected from smartphones and wearable devices. Before that, he was a Research Scientist and one of the founding members of Apple’s Health AI team, where he focused on advancing machine learning for health-related applications. Gatys’ academic background is equally notable. During his PhD, under the supervision of Prof. Matthias Bethge, he pioneered the development of Neural Style Transfer, a groundbreaking algorithm that became one of the earliest demonstrations of the creative potential of generative AI. This work has had a lasting impact on both AI research and the broader cultural imagination of what artificial intelligence can achieve.