Artistic style transfer for videos

Abstract

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.

final version appeared in GCPR-2016; minor changes to improve the clarity

Cited by in corpus (11)

• DeepXplore: Automated Whitebox Testing of Deep Learning Systems
• Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation
• Artistic style transfer for videos and spherical images
• A survey of synthetic data augmentation methods in computer vision
• A Multi-Pass GAN for Fluid Flow Super-Resolution
• Transport-Based Neural Style Transfer for Smoke Simulations
• Optical Flow Distillation: Towards Efficient and Stable Video Style Transfer
• VCGAN: Video Colorization with Hybrid Generative Adversarial Network
• Evaluation in Neural Style Transfer: A Review
• MVStylizer: An Efficient Edge-Assisted Video Photorealistic Style Transfer System for Mobile Phones
• Iris Style Transfer: Enhancing Iris Recognition with Style Features and Privacy Preservation through Neural Style Transfer