首页 | 本学科首页   官方微博 | 高级检索  
     

深度图像超分辨率重建技术综述
引用本文:李滔,董秀成,张晓华. 深度图像超分辨率重建技术综述[J]. 西华大学学报(自然科学版), 2020, 39(4): 45-53. DOI: 10.12198/j.issn.1673-159X.3585
作者姓名:李滔  董秀成  张晓华
作者单位:西华大学电气与电子信息学院,四川成都 610065;广岛工业大学,日本广岛 7315193
基金项目:国家自然科学基金资助项目(61901392);西华大学人才引进项目(Z201011)
摘    要:便携式消费级深度相机的问世和发展,加速了深度信息在无人驾驶、人机交互、三维重建等领域的应用,但低成本消费级相机所拍摄的深度图像通常具有较低的空间分辨率。深度图像超分辨率重建是一种能有效提高深度信息空间分辨率的方法,已经成为计算机视觉和图像处理领域的研究热点。在详细阐述深度图像超分辨率重建概念和必要性的基础上,从输入图像角度,全面梳理归纳了近年来深度图像超分辨率重建方法的研究现状,对其中的关键性问题和今后的研究方向做了较为深入的分析,最后对深度图像超分辨率重建的应用前景进行了展望。

关 键 词:深度图像  超分辨率重建  彩色引导  卷积神经网络  深度学习
收稿时间:2020-03-10

A Survey of Super-Resolution Reconstruction Technologies for Depth Image
LI Tao,DONG Xiucheng,ZHANG Xiaohua. A Survey of Super-Resolution Reconstruction Technologies for Depth Image[J]. Journal of Xihua University(Natural Science Edition), 2020, 39(4): 45-53. DOI: 10.12198/j.issn.1673-159X.3585
Authors:LI Tao  DONG Xiucheng  ZHANG Xiaohua
Affiliation:1.School of Electrical Engineering and Electronic Information, Xihua University, Chengdu 610065 China
Abstract:The advent and development of portable consumer-grade cameras accelerate the use of depth information in many application fields, such as autonomous navigation, human computer interaction, and 3D reconstruction. However, depth images captured by these low-cost cameras usually have very low spatial resolutions. Depth image super-resolution (DISR) is an effective way to improve the spatial resolution of depth information, which has been a research focus in computer vision and image processing fields. The concept and necessity of DISR are described in detail in this paper. In addition, the DISR methods in recent years are comprehensively reviewed from the perspective of input image. Some of the key technologies and the development trend are analyzed. And the application prospect of DISR are provided at the end of this paper.
Keywords:
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《西华大学学报(自然科学版)》浏览原始摘要信息
点击此处可从《西华大学学报(自然科学版)》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号