TL;DR
This paper introduces two novel computational methods for transferring artistic styles to videos and spherical images, enabling consistent, stable, and nearly real-time stylization suitable for virtual reality content.
Contribution
It presents a new energy minimization technique and a deep learning approach for video style transfer, including adaptation to 360-degree images and videos.
Findings
The deep learning method achieves nearly real-time stylization.
Both methods outperform simpler baselines in quality and consistency.
The approaches are adaptable to VR content with spherical images and videos.
Abstract
Manually re-drawing an image in a certain artistic style takes a professional artist a long time. Doing this for a video sequence single-handedly is beyond imagination. We present two computational approaches that transfer the style from one image (for example, a painting) to a whole video sequence. In our first approach, we adapt to videos the original image style transfer technique by Gatys et al. based on energy minimization. We introduce new ways of initialization and new loss functions to generate consistent and stable stylized video sequences even in cases with large motion and strong occlusion. Our second approach formulates video stylization as a learning problem. We propose a deep network architecture and training procedures that allow us to stylize arbitrary-length videos in a consistent and stable way, and nearly in real time. We show that the proposed methods clearly…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
