Renoir Tuebingen, Earliest Tuebingen Variants, February
Still, 2015
Buy Now $12000
View full-resolution artwork ↗Loading auction…
About the artwork
These are the very first images ever generated with Neural Style Transfer. At that time, the algorithm was still in its very early stages as can be seen from the low resolution of the images and the lower stylization quality compared to the later images. When we saw these first results we knew we were on to something significant, even though we still hadn't fully wrapped our head around it because it was completely new and unprecedented at the time(1). So when I first presented these results in a Bethgelab group meeting on February 27th, 2015 I had a discussion slide with the bullet "- Artistic images: what to do with them?". How the algorithm improved over the coming months can be best seen by comparing the "Chagall Tuebingen" early variant, with the "Ri Tuebingen Neckarfront - Gi Chagall Lovers At Vence" image which was generated with the full algorithm presented in the A Neural Algorithm of Artistic Style paper but ultimately not included in the paper.
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.