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

Electron Microscope Tomography and Single-particle Reconstruction01:07

Electron Microscope Tomography and Single-particle Reconstruction

Transmission electron microscopy (TEM) can be used to determine the 3D structure of biological samples with the help of techniques such as electron microscope tomography and single-particle reconstruction. While single-particle reconstruction can examine macromolecules and macromolecular complexes in vitro conditions only, tomography permits the study of cell components or small cells in vivo.
Electron Tomography
Electron tomography can be performed either in TEM or STEM (scanning transmission...

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

Spectral Image Rendering of Fluorescent Objects Using a Conventional Renderer.

IEEE transactions on visualization and computer graphics·2026
Same author

Relationship Between Display Pixel Structure and Gloss Perception.

Journal of imaging·2026
Same author

Roughness Estimation and Image Rendering for Glossy Object Surface.

Journal of imaging·2025
Same author

Relationship Between Darkness and Healing of Night Sky in Planetarium.

International journal of environmental research and public health·2025
Same author

Analysis of Physical Features Affecting Glossiness and Roughness Alteration in Image Reproduction and Image Features for Their Recovery.

Journal of imaging·2025
Same author

Impact of Display Pixel-Aperture Ratio on Perceived Roughness, Glossiness, and Transparency.

Journal of imaging·2025

相关实验视频

Updated: Jun 6, 2026

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects
10:16

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

12.3K

从金属物体的和图像进行高动态范围图像重建.

Shoji Tominaga1,2, Takahiko Horiuchi3

  • 1Department of Computer Science, Norwegian University of Science and Technology, 2815 Gjøvik, Norway.

Journal of imaging
|April 26, 2024
PubMed
概括

本研究介绍了一个深度神经网络,可以从金属物体的单个低动态范围 (LDR) 图像中重建高动态范围 (HDR) 图像. 这种新的方法显著提高了HDR成像的重建精度和视觉质量.

关键词:
图像数据库中的HDR图像数据库.从LDR到HDR的映射映射深度神经网络的方法.亮光感知 感知 亮光感知高动态范围图像重建图像重建人类心理实验 人类心理实验物质的外观物质的外观金属物体是金属物体.重建和光泽的复制.和的低动态范围图像

更多相关视频

Identification of Metal Oxide Nanoparticles in Histological Samples by Enhanced Darkfield Microscopy and Hyperspectral Mapping
12:19

Identification of Metal Oxide Nanoparticles in Histological Samples by Enhanced Darkfield Microscopy and Hyperspectral Mapping

Published on: December 8, 2015

12.5K
Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.4K

相关实验视频

Last Updated: Jun 6, 2026

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects
10:16

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

12.3K
Identification of Metal Oxide Nanoparticles in Histological Samples by Enhanced Darkfield Microscopy and Hyperspectral Mapping
12:19

Identification of Metal Oxide Nanoparticles in Histological Samples by Enhanced Darkfield Microscopy and Hyperspectral Mapping

Published on: December 8, 2015

12.5K
Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.4K

科学领域:

  • 计算机视觉 计算机视觉
  • 图像处理 图像处理
  • 深度学习 (Deep Learning) 是一种深度学习.

背景情况:

  • 从低动态范围 (LDR) 图像中重建高动态范围 (HDR) 图像是具有挑战性的,特别是对于金属物体,因为它们的反射特性.
  • 在处理复杂材料表面时,现有的方法往往在准确性和视觉准确性方面扎.

研究的目的:

  • 开发一个深度神经网络,从金属物体的单个和LDR图像直接重建HDR图像.
  • 为了提高对具有挑战性的材料的HDR图像重建的准确性和视觉质量.

主要方法:

  • 一个深度神经网络,特别是类似U-Net的卷积神经网络 (CNN) 架构,被设计用于从8位LDR到HDR图像的直接映射.
  • 创建了一个金属物体的HDR图像数据库,并剪切HDR图像以生成相应的LDR图像用于训练和测试.
  • 该CNN包括一个编码器,解码器和跳过连接,利用MATLAB进行32层和85,900个可学习参数的算法构建.

主要成果:

  • 拟议的CNN方法在从LDR输入中重建HDR图像方面表现出卓越的性能.
  • 实验评估证实,与现有方法相比,重建准确度,组图匹配度和主观视觉质量有显著改善.
  • 类似于U-Net的架构在整个重建过程中有效地保留了图像分辨率.

结论:

  • 深度神经网络方法为从金属物体的单个LDR图像中进行HDR图像重建提供了强大的和有效的解决方案.
  • 该方法显著优于传统技术,提供更准确和视觉上更令人愉快的HDR结果.
  • 这项工作推动了HDR成像领域的发展,特别是在涉及反射和金属表面的应用中.