Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

A hypoxia-responsive migrasome-related lncRNA signature predicts prognosis and suggests the MSC-AS1/ITGA5 axis as a potential therapeutic target in head and neck squamous cell carcinoma.

Functional & integrative genomics·2026
Same author

SA-RAG: Structured and adaptive retrieval-augmented generation for multi-hop question answering.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Development and validation of a noninvasive machine learning model using urinary extracellular vesicle physical parameters for prostate cancer diagnosis.

Scientific reports·2026
Same author

Integrating single-cell and bulk transcriptomic analyses to explore key lactylation-related genes in benign prostatic hyperplasia.

Scientific reports·2026
Same author

Yeast surface display-based screening and preliminary characterization of nectin-4-targeting nanobodies for bladder cancer.

BMC biotechnology·2026
Same author

Deep learning-driven performance prediction and design of high-DoF MEMS resonators.

Microsystems & nanoengineering·2026

相关实验视频

Updated: Sep 15, 2025

Group Synchronization During Collaborative Drawing Using Functional Near-Infrared Spectroscopy
07:53

Group Synchronization During Collaborative Drawing Using Functional Near-Infrared Spectroscopy

Published on: August 5, 2022

2.1K

西藏绘画素描提取的扩散概率模型.

Fubo Wang1,2,3, Shengling Geng4,5,6, Zeyu Jia1,2,3

  • 1Qinghai Normal University, School of Computer Science, Xining, 810008, China.

Scientific reports
|July 16, 2025
PubMed
概括
此摘要是机器生成的。

使用扩散概率模型 (DPM) 的新方法DiffusionSketch有效提取清晰的西藏绘画草图. 这种方法在主观和客观评估中显著改进了现有的方法.

更多相关视频

An Inverse Analysis Approach to the Characterization of Chemical Transport in Paints
08:42

An Inverse Analysis Approach to the Characterization of Chemical Transport in Paints

Published on: August 29, 2014

8.5K
Creating Dynamic Images of Short-lived Dopamine Fluctuations with lp-ntPET: Dopamine Movies of Cigarette Smoking
14:21

Creating Dynamic Images of Short-lived Dopamine Fluctuations with lp-ntPET: Dopamine Movies of Cigarette Smoking

Published on: August 6, 2013

18.4K

相关实验视频

Last Updated: Sep 15, 2025

Group Synchronization During Collaborative Drawing Using Functional Near-Infrared Spectroscopy
07:53

Group Synchronization During Collaborative Drawing Using Functional Near-Infrared Spectroscopy

Published on: August 5, 2022

2.1K
An Inverse Analysis Approach to the Characterization of Chemical Transport in Paints
08:42

An Inverse Analysis Approach to the Characterization of Chemical Transport in Paints

Published on: August 29, 2014

8.5K
Creating Dynamic Images of Short-lived Dopamine Fluctuations with lp-ntPET: Dopamine Movies of Cigarette Smoking
14:21

Creating Dynamic Images of Short-lived Dopamine Fluctuations with lp-ntPET: Dopamine Movies of Cigarette Smoking

Published on: August 6, 2013

18.4K

科学领域:

  • 计算机视觉 计算机视觉
  • 人工智能的人工智能
  • 数字艺术保护数字艺术保护

背景情况:

  • 西藏绘画需要精细的草图,经常为不同的艺术品重新绘制相同的图案.
  • 提取这些复杂的草图是至关重要的,但由于复杂的细节,具有挑战性.
  • 现有的方法与藏族艺术特有的细线和颜色作斗争.

研究的目的:

  • 开发一种自动化方法,从藏文绘画中提取高保真素描.
  • 为了解决复杂的文化艺术作品当前素描提取技术的局限性.
  • 引入基于扩散概率模型 (DPM) 的方法,用于增强草图生成.

主要方法:

  • 拟议的 DiffusionSketch 方法使用 DPM 来提取草图.
  • 两个阶段的特征提取捕捉全球和本地背景.
  • 适应波纹波器和功能融合模块 (FFM) 进行功能集成.
  • 生成对抗网络 (GAN) 用于改进草图输出并最大限度地减少扭曲.

主要成果:

  • DiffusionSketch可以生成清晰,简洁,低噪音的西藏绘画草图.
  • 该方法在河黄藏色绘画 (HHTP) 数据集上表现出卓越的性能.
  • 在36种方法中获得了最高排名,在主观 (57.12%) 和客观 (18.30%) 评估中取得了显著的改进.

结论:

  • DiffusionSketch提供了一种高效和有效的解决方案,用于提取西藏绘画素描.
  • 基于DPM的方法成功地保留了复杂的细节和艺术品质.
  • 这种方法为数字保存和复制文化艺术提供了有价值的工具.