Image Style Transfer and Content-Style Disentanglement

Abstract

We propose a way of learning disentangled content-style representation of image, allowing us to extrapolate images to any style as well as interpolate between any pair of styles. By augmenting data set in a supervised setting and imposing triplet loss, we ensure the separation of information encoded by content and style representation. We also make use of cycle-consistency loss to guarantee that images could be reconstructed faithfully by their representation.

10 pages, 6 figures

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Instance Normalization: The Missing Ingredient for Fast Stylization
• A Learned Representation For Artistic Style
• Disentangling factors of variation in deep representations using adversarial training
• Multi-style Generative Network for Real-time Transfer
• PixelVAE: A Latent Variable Model for Natural Images

Cited by in corpus (1)

• Shared Manifold Learning Using a Triplet Network for Multiple Sensor Translation and Fusion with Missing Data