Artistic Style Transfer for Videos

From Manuel Ruder, Alexey Dosovitskiy, Thomas Brox of the University of Freiburg:

In the past, manually re-drawing an image in a certain artistic style required a professional artist and a long time. Doing this for a video sequence single-handed was beyond imagination. Nowadays computers provide new possibilities. We present an approach that transfers the style from one image (for example, a painting) to a whole video sequence. We make use of recent advances in style transfer in still images and propose new initializations and loss functions applicable to videos. This allows us to generate consistent and stable stylized video sequences, even in cases with large motion and strong occlusion. We show that the proposed method clearly outperforms simpler baselines both qualitatively and quantitatively... (pdf paper)

 

Featured Product

Basler 3D Vision Solutions for Robotics and Warehouse Automation

Basler 3D Vision Solutions for Robotics and Warehouse Automation

Empower your robot's vision: with our 3D cameras and tailored robotics application software, your robot can tackle any task. From bin picking to sorting and navigation, AI enables your robot to recognize even "unseen" objects in mixed scenarios. Explore our time-of-flight and stereo cameras for vision-guided robotics with a wide range of compatible accessories."