Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration

Abstract

Zero-shot artistic style transfer is an important image synthesis problem aiming at transferring arbitrary style into content images. However, the trade-off between the generalization and efficiency in existing methods impedes a high quality zero-shot style transfer in real-time. In this paper, we resolve this dilemma and propose an efficient yet effective Avatar-Net that enables visually plausible multi-scale transfer for arbitrary style. The key ingredient of our method is a style decorator that makes up the content features by semantically aligned style features from an arbitrary style image, which does not only holistically match their feature distributions but also preserve detailed style patterns in the decorated features. By embedding this module into an image reconstruction network that fuses multi-scale style abstractions, the Avatar-Net renders multi-scale stylization for any style image in one feed-forward pass. We demonstrate the state-of-the-art effectiveness and efficiency of the proposed method in generating high-quality stylized images, with a series of applications include multiple style integration, video stylization and etc.

arXiv commentAccepted at CVPR 2018

References in corpus (17)

• A Learned Representation For Artistic Style
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
• Optimal whitening and decorrelation
• Texture Synthesis Using Convolutional Neural Networks
• Fast Patch-based Style Transfer of Arbitrary Style
• Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks
• Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses
• Style-Transfer via Texture-Synthesis
• Multi-style Generative Network for Real-time Transfer
• Demystifying Neural Style Transfer
• StyleBank: An Explicit Representation for Neural Image Style Transfer
• Coherent Online Video Style Transfer
• Visual Attribute Transfer through Deep Image Analogy
• ZM-Net: Real-time Zero-shot Image Manipulation Network
• Meta Networks for Neural Style Transfer
• Characterizing and Improving Stability in Neural Style Transfer
• Stereoscopic Neural Style Transfer

Cited by in corpus (8)

• Learning Linear Transformations for Fast Arbitrary Style Transfer
• Dynamic Instance Normalization for Arbitrary Style Transfer
• Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping
• Stereoscopic Neural Style Transfer
• Diversified Arbitrary Style Transfer via Deep Feature Perturbation
• Learning from Multi-domain Artistic Images for Arbitrary Style Transfer
• EFANet: Exchangeable Feature Alignment Network for Arbitrary Style Transfer
• CAMS: Color-Aware Multi-Style Transfer