Saved in:
Bibliographic Details
Main Authors: Guo, Wei, Zhang, Yuqi, Ma, De, Zheng, Qian
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.13976
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929223697956864
author Guo, Wei
Zhang, Yuqi
Ma, De
Zheng, Qian
author_facet Guo, Wei
Zhang, Yuqi
Ma, De
Zheng, Qian
contents Recent advancement in computer vision has significantly lowered the barriers to artistic creation. Exemplar-based image translation methods have attracted much attention due to flexibility and controllability. However, these methods hold assumptions regarding semantics or require semantic information as the input, while accurate semantics is not easy to obtain in artistic images. Besides, these methods suffer from cross-domain artifacts due to training data prior and generate imprecise structure due to feature compression in the spatial domain. In this paper, we propose an arbitrary Style Image Manipulation Network (SIM-Net), which leverages semantic-free information as guidance and a region transportation strategy in a self-supervised manner for image generation. Our method balances computational efficiency and high resolution to a certain extent. Moreover, our method facilitates zero-shot style image manipulation. Both qualitative and quantitative experiments demonstrate the superiority of our method over state-of-the-art methods.Code is available at https://github.com/SnailForce/SIM-Net.
format Preprint
id arxiv_https___arxiv_org_abs_2401_13976
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning to Manipulate Artistic Images
Guo, Wei
Zhang, Yuqi
Ma, De
Zheng, Qian
Computer Vision and Pattern Recognition
Artificial Intelligence
Recent advancement in computer vision has significantly lowered the barriers to artistic creation. Exemplar-based image translation methods have attracted much attention due to flexibility and controllability. However, these methods hold assumptions regarding semantics or require semantic information as the input, while accurate semantics is not easy to obtain in artistic images. Besides, these methods suffer from cross-domain artifacts due to training data prior and generate imprecise structure due to feature compression in the spatial domain. In this paper, we propose an arbitrary Style Image Manipulation Network (SIM-Net), which leverages semantic-free information as guidance and a region transportation strategy in a self-supervised manner for image generation. Our method balances computational efficiency and high resolution to a certain extent. Moreover, our method facilitates zero-shot style image manipulation. Both qualitative and quantitative experiments demonstrate the superiority of our method over state-of-the-art methods.Code is available at https://github.com/SnailForce/SIM-Net.
title Learning to Manipulate Artistic Images
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2401.13976