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 at the University of Freiburg developed a new style transfer algorithm that applies artistic styles from paintings to video content.
- The technique uses cuDNN deep learning software and NVIDIA TITAN X GPUs to extract style from a source painting and synthesize it with video frames.
- Applying style transfer frame by frame causes flickering, so the team introduced additional constraints to maintain temporal consistency across the video sequence.
- GPU acceleration is essential because the style transfer process is computationally intensive and time consuming.
Next Step
- Read the deep learning paints videos blog post for the full technical details.
Powered by NVIDIA Nemotron. AI-generated content may summarize information incompletely. Verify important information. Learn more
About the Authors
