Saved in:
Bibliographic Details
Main Authors: Zheng, Sizhe, Gao, Pan, Zhou, Peng, Qin, Jie
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.19775
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916265875996672
author Zheng, Sizhe
Gao, Pan
Zhou, Peng
Qin, Jie
author_facet Zheng, Sizhe
Gao, Pan
Zhou, Peng
Qin, Jie
contents Style transfer aims to render an image with the artistic features of a style image, while maintaining the original structure. Various methods have been put forward for this task, but some challenges still exist. For instance, it is difficult for CNN-based methods to handle global information and long-range dependencies between input images, for which transformer-based methods have been proposed. Although transformers can better model the relationship between content and style images, they require high-cost hardware and time-consuming inference. To address these issues, we design a novel transformer model that includes only the encoder, thus significantly reducing the computational cost. In addition, we also find that existing style transfer methods may lead to images under-stylied or missing content. In order to achieve better stylization, we design a content feature extractor and a style feature extractor, based on which pure content and style images can be fed to the transformer. Finally, we propose a novel network termed Puff-Net, i.e., pure content and style feature fusion network. Through qualitative and quantitative experiments, we demonstrate the advantages of our model compared to state-of-the-art ones in the literature.
format Preprint
id arxiv_https___arxiv_org_abs_2405_19775
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network
Zheng, Sizhe
Gao, Pan
Zhou, Peng
Qin, Jie
Computer Vision and Pattern Recognition
Style transfer aims to render an image with the artistic features of a style image, while maintaining the original structure. Various methods have been put forward for this task, but some challenges still exist. For instance, it is difficult for CNN-based methods to handle global information and long-range dependencies between input images, for which transformer-based methods have been proposed. Although transformers can better model the relationship between content and style images, they require high-cost hardware and time-consuming inference. To address these issues, we design a novel transformer model that includes only the encoder, thus significantly reducing the computational cost. In addition, we also find that existing style transfer methods may lead to images under-stylied or missing content. In order to achieve better stylization, we design a content feature extractor and a style feature extractor, based on which pure content and style images can be fed to the transformer. Finally, we propose a novel network termed Puff-Net, i.e., pure content and style feature fusion network. Through qualitative and quantitative experiments, we demonstrate the advantages of our model compared to state-of-the-art ones in the literature.
title Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.19775