Deep Learning Helps Transfer Famous Artistic Styles to Videos

A new style transfer algorithm makes clips from Ice Age appear as paintings in the style of van Gogh’s “Starry Night”.

Researchers from University of Freiburg in Germany are using cuDNN deep learning software and NVIDIA TITAN X GPUs to extract a specific artistic style from a source painting, and then synthesizes this information with the content of a separate video.

The team builds upon previous work of applying artistic styles to images – but extending this technique for videos is more challenging.

“If you just apply the algorithm frame by frame, you don’t get a coherent video — you get flickering in the sequence,” says University of Freiburg postdoc Alexey Dosovitskiy. “What we do is introduce additional constraints, which make the video consistent.”

“GPUs are crucial because this process is quite time consuming,” Dosovitskiy says.

Read more >

About Brad Nemire

Brad Nemire
Brad Nemire is on the Developer Marketing team and loves reading about all of the fascinating research being done by developers using NVIDIA GPUs. Reach out to Brad on Twitter @BradNemire and let him know how you’re using GPUs to accelerate your research. Brad graduated from San Diego State University and currently resides in San Jose, CA. Follow @BradNemire on Twitter