StyleBank: An Explicit Representation for Neural Image Style Transfer

Abstract

We propose StyleBank, which is composed of multiple convolution filter banks and each filter bank explicitly represents one style, for neural image style transfer. To transfer an image to a specific style, the corresponding filter bank is operated on top of the intermediate feature embedding produced by a single auto-encoder. The StyleBank and the auto-encoder are jointly learnt, where the learning is conducted in such a way that the auto-encoder does not encode any style information thanks to the flexibility introduced by the explicit filter bank representation. It also enables us to conduct incremental learning to add a new image style by learning a new filter bank while holding the auto-encoder fixed. The explicit style representation along with the flexible network design enables us to fuse styles at not only the image level, but also the region level. Our method is the first style transfer network that links back to traditional texton mapping methods, and hence provides new understanding on neural style transfer. Our method is easy to train, runs in real-time, and produces results that qualitatively better or at least comparable to existing methods.

Accepted by CVPR 2017, corrected typos

References in corpus (2)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks

Cited by in corpus (21)

• Coherent Online Video Style Transfer
• Gated Context Aggregation Network for Image Dehazing and Deraining
• Style Transfer for Anime Sketches with Enhanced Residual U-net and Auxiliary Classifier GAN
• Visual Attribute Transfer through Deep Image Analogy
• ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows
• Dynamic Instance Normalization for Arbitrary Style Transfer
• Rethinking and Improving the Robustness of Image Style Transfer
• Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture
• Unsupervised Multi-Domain Image Translation with Domain-Specific Encoders/Decoders
• Chinese Typeface Transformation with Hierarchical Adversarial Network
• Neural Abstract Style Transfer for Chinese Traditional Painting
• Learning to Caricature via Semantic Shape Transform
• Domain-Specific Mappings for Generative Adversarial Style Transfer
• Im2Pencil: Controllable Pencil Illustration from Photographs
• Learning to Forecast Videos of Human Activity with Multi-granularity Models and Adaptive Rendering
• A Method for Arbitrary Instance Style Transfer
• Synthesis of High-Quality Visible Faces from Polarimetric Thermal Faces using Generative Adversarial Networks
• Non-Parametric Neural Style Transfer
• Artistic Object Recognition by Unsupervised Style Adaptation
• TAN: Temporal Aggregation Network for Dense Multi-label Action Recognition
• Learning to Transfer Visual Effects from Videos to Images