Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration
This work addresses the problem of efficient and generalized style transfer for users in image synthesis, offering a novel method that balances quality and speed, though it builds on existing paradigms.
The paper tackled the trade-off between generalization and efficiency in zero-shot artistic style transfer by proposing Avatar-Net, which enables high-quality, multi-scale style transfer for arbitrary styles in real-time, achieving state-of-the-art results with improved speed and visual plausibility.
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.