Coherent Online Video Style Transfer

TL;DR

This paper introduces an end-to-end neural network for online video style transfer that produces temporally coherent stylized videos in near real-time, significantly improving over frame-by-frame methods.

Contribution

It presents the first efficient, end-to-end network for online video style transfer that maintains temporal coherence over long sequences.

Findings

Outperforms per-frame baseline qualitatively and quantitatively

Achieves comparable coherence to optimization-based methods

Runs three orders of magnitude faster than existing approaches

Abstract

Training a feed-forward network for fast neural style transfer of images is proven to be successful. However, the naive extension to process video frame by frame is prone to producing flickering results. We propose the first end-to-end network for online video style transfer, which generates temporally coherent stylized video sequences in near real-time. Two key ideas include an efficient network by incorporating short-term coherence, and propagating short-term coherence to long-term, which ensures the consistency over larger period of time. Our network can incorporate different image stylization networks. We show that the proposed method clearly outperforms the per-frame baseline both qualitatively and quantitatively. Moreover, it can achieve visually comparable coherence to optimization-based video style transfer, but is three orders of magnitudes faster in runtime.