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 >
Deep Learning Helps Transfer Famous Artistic Styles to Videos
Jun 01, 2016
Discuss (0)
AI-Generated Summary
- Researchers from the University of Freiburg are using NVIDIA TITAN X GPUs and cuDNN deep learning software to develop a style transfer algorithm that can make videos appear as paintings in a specific artistic style.
- The team, including Alexey Dosovitskiy, is building upon previous work that applied artistic styles to images, but is introducing additional constraints to make the video output consistent and avoid flickering.
- The new algorithm can transform video clips, such as those from Ice Age, into paintings in the style of famous artworks like Vincent van Gogh's Starry Night.
AI-generated content may summarize information incompletely. Verify important information. Learn more
About the Authors
