ETNet: Error Transition Network for Arbitrary Style Transfer

10/26/2019
by   Chunjin Song, et al.
31

Numerous valuable efforts have been devoted to achieving arbitrary style transfer since the seminal work of Gatys et al. However, existing state-of-the-art approaches often generate insufficiently stylized results under challenging cases. We believe a fundamental reason is that these approaches try to generate the stylized result in a single shot and hence fail to fully satisfy the constraints on semantic structures in the content images and style patterns in the style images. Inspired by the works on error-correction, instead, we propose a self-correcting model to predict what is wrong with the current stylization and refine it accordingly in an iterative manner. For each refinement, we transit the error features across both the spatial and scale domain and invert the processed features into a residual image, with a network we call Error Transition Network (ETNet). The proposed model improves over the state-of-the-art methods with better semantic structures and more adaptive style pattern details. Various qualitative and quantitative experiments show that the key concept of both progressive strategy and error-correction leads to better results. Code and models are available at https://github.com/zhijieW94/ETNet.

READ FULL TEXT

page 2

page 6

page 7

page 8

research
05/19/2022

Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning

In this work, we tackle the challenging problem of arbitrary image style...
research
05/27/2020

Arbitrary Style Transfer via Multi-Adaptation Network

Arbitrary style transfer is a significant topic with both research value...
research
08/27/2022

AesUST: Towards Aesthetic-Enhanced Universal Style Transfer

Recent studies have shown remarkable success in universal style transfer...
research
12/08/2022

All-to-key Attention for Arbitrary Style Transfer

Attention-based arbitrary style transfer studies have shown promising pe...
research
03/27/2019

Grammatical Error Correction and Style Transfer via Zero-shot Monolingual Translation

Both grammatical error correction and text style transfer can be viewed ...
research
03/23/2019

Photorealistic Style Transfer via Wavelet Transforms

Recent style transfer models have provided promising artistic results. H...
research
10/07/2020

A Self-Refinement Strategy for Noise Reduction in Grammatical Error Correction

Existing approaches for grammatical error correction (GEC) largely rely ...

Please sign up or login with your details

Forgot password? Click here to reset