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

05/10/2018
by   Lu Sheng, et al.
2

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.

READ FULL TEXT

page 4

page 6

page 7

page 8

page 10

page 11

page 12

page 13

research
09/27/2019

Style Transfer by Rigid Alignment in Neural Net Feature Space

Arbitrary style transfer is an important problem in computer vision that...
research
03/21/2017

ZM-Net: Real-time Zero-shot Image Manipulation Network

Many problems in image processing and computer vision (e.g. colorization...
research
06/07/2019

Conditional Neural Style Transfer with Peer-Regularized Feature Transform

This paper introduces a neural style transfer model to conditionally gen...
research
03/19/2023

StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fields

3D style transfer aims to render stylized novel views of a 3D scene with...
research
04/24/2023

Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer

Transformer-based models achieve favorable performance in artistic style...
research
08/09/2023

VAST: Vivify Your Talking Avatar via Zero-Shot Expressive Facial Style Transfer

Current talking face generation methods mainly focus on speech-lip synch...
research
08/13/2021

UMFA: A photorealistic style transfer method based on U-Net and multi-layer feature aggregation

In this paper, we propose a photorealistic style transfer network to emp...

Please sign up or login with your details

Forgot password? Click here to reset