• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于引导的神经风格迁移的形状风格化。

Guided neural style transfer for shape stylization.

机构信息

Department of Advanced Information Technology, Kyushu University, Fukuoka, Japan.

出版信息

PLoS One. 2020 Jun 4;15(6):e0233489. doi: 10.1371/journal.pone.0233489. eCollection 2020.

DOI:10.1371/journal.pone.0233489
PMID:32497055
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC7272093/
Abstract

Designing logos, typefaces, and other decorated shapes can require professional skills. In this paper, we aim to produce new and unique decorated shapes by stylizing ordinary shapes with machine learning. Specifically, we combined parametric and non-parametric neural style transfer algorithms to transfer both local and global features. Furthermore, we introduced a distance-based guiding to the neural style transfer process, so that only the foreground shape will be decorated. Lastly, qualitative evaluation and ablation studies are provided to demonstrate the usefulness of the proposed method.

摘要

设计标志、字体和其他装饰形状可能需要专业技能。在本文中，我们旨在通过使用机器学习对普通形状进行样式化来生成新的和独特的装饰形状。具体来说，我们结合了参数和非参数神经风格转移算法来转移局部和全局特征。此外，我们在神经风格转移过程中引入了基于距离的引导，以便仅对前景形状进行装饰。最后，提供了定性评估和消融研究，以证明所提出方法的有效性。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/057c5216eca3/pone.0233489.g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/e74056586e44/pone.0233489.g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/e103ef5481c4/pone.0233489.g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/a205cb3e62cb/pone.0233489.g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/d033858a3d38/pone.0233489.g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/f9005e865776/pone.0233489.g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/1a85615a1586/pone.0233489.g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/5dbf5de2e473/pone.0233489.g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/5fb9e9d7b045/pone.0233489.g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/dca6f4577260/pone.0233489.g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/0cb9d8cf8928/pone.0233489.g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/bface620376a/pone.0233489.g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/b377fb57876f/pone.0233489.g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/f01b13291eb9/pone.0233489.g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/927842bcc8d2/pone.0233489.g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/16a9852e5dc8/pone.0233489.g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/0a4bd9a8156d/pone.0233489.g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/057c5216eca3/pone.0233489.g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/e74056586e44/pone.0233489.g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/e103ef5481c4/pone.0233489.g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/a205cb3e62cb/pone.0233489.g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/d033858a3d38/pone.0233489.g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/f9005e865776/pone.0233489.g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/1a85615a1586/pone.0233489.g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/5dbf5de2e473/pone.0233489.g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/5fb9e9d7b045/pone.0233489.g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/dca6f4577260/pone.0233489.g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/0cb9d8cf8928/pone.0233489.g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/bface620376a/pone.0233489.g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/b377fb57876f/pone.0233489.g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/f01b13291eb9/pone.0233489.g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/927842bcc8d2/pone.0233489.g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/16a9852e5dc8/pone.0233489.g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/0a4bd9a8156d/pone.0233489.g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7865/7272093/057c5216eca3/pone.0233489.g017.jpg

相似文献

1
Guided neural style transfer for shape stylization.基于引导的神经风格迁移的形状风格化。
PLoS One. 2020 Jun 4;15(6):e0233489. doi: 10.1371/journal.pone.0233489. eCollection 2020.
2
NeRF-Art: Text-Driven Neural Radiance Fields Stylization.NeRF-Art：文本驱动的神经辐射场风格化
IEEE Trans Vis Comput Graph. 2024 Aug;30(8):4983-4996. doi: 10.1109/TVCG.2023.3283400. Epub 2024 Jul 1.
3
Molecular graph convolutions: moving beyond fingerprints.分子图卷积：超越指纹图谱
J Comput Aided Mol Des. 2016 Aug;30(8):595-608. doi: 10.1007/s10822-016-9938-8. Epub 2016 Aug 24.
4
Predicting Market Impact Costs Using Nonparametric Machine Learning Models.使用非参数机器学习模型预测市场冲击成本。
PLoS One. 2016 Feb 29;11(2):e0150243. doi: 10.1371/journal.pone.0150243. eCollection 2016.
5
A Foreground-Aware Framework for Local Face Attribute Transfer.一种用于局部面部属性转移的前景感知框架。
Entropy (Basel). 2021 May 16;23(5):615. doi: 10.3390/e23050615.
6
Point-based computer graphics.基于点的计算机图形学。
IEEE Comput Graph Appl. 2004 Jul-Aug;24(4):22-3. doi: 10.1109/mcg.2004.15.
7
Video painting with space-time-varying style parameters.视频绘画的时空变化风格参数。
IEEE Trans Vis Comput Graph. 2011 Jan;17(1):74-87. doi: 10.1109/TVCG.2010.25.
8
Context-dependent logo matching and recognition.上下文相关的徽标匹配和识别。
IEEE Trans Image Process. 2013 Mar;22(3):1018-31. doi: 10.1109/TIP.2012.2226046. Epub 2012 Oct 22.
9
Optimized synthesis of art patterns and layered textures.艺术图案和分层纹理的优化合成。
IEEE Trans Vis Comput Graph. 2014 Mar;20(3):436-46. doi: 10.1109/TVCG.2013.113.
10
Context-Aware Text-Based Binary Image Stylization and Synthesis.基于上下文感知的文本驱动二值图像风格化与合成
IEEE Trans Image Process. 2018 Oct 1. doi: 10.1109/TIP.2018.2873064.

引用本文的文献

1
Self-supervised VICReg pre-training for Brugada ECG detection.用于Brugada心电图检测的自监督VICReg预训练
Sci Rep. 2025 Mar 19;15(1):9396. doi: 10.1038/s41598-025-94130-x.

本文引用的文献

1
Improved Deformation-Driven Element Packing with RepulsionPak.使用RepulsionPak改进变形驱动的单元填充。
IEEE Trans Vis Comput Graph. 2021 Apr;27(4):2396-2408. doi: 10.1109/TVCG.2019.2950235. Epub 2021 Feb 25.
2
Neural Style Transfer: A Review.神经风格迁移：综述。
IEEE Trans Vis Comput Graph. 2020 Nov;26(11):3365-3385. doi: 10.1109/TVCG.2019.2921336. Epub 2019 Jun 6.