基于两视点的任意虚拟视点图像合成

梁华刚; 孙小喃; 茹锋

doi:10.3788/OPE.20152313.0713

您当前的位置：

首页 >

文章列表页 >

基于两视点的任意虚拟视点图像合成

更新时间：2020-08-13

- 基于两视点的任意虚拟视点图像合成
- Image synthesis of arbitrary virtual viewpoint based on two viewpoints
- 光学精密工程 2015年23卷第10z期页码：712-721
- 作者机构：
  
  长安大学电子与控制工程学院,陕西西安,710064
- 作者简介：
- 基金信息：
  
  国家自然科学基金青年基金资助项目(No.61203374)();陕西省自然科学基金国际合作项目(No.2014KW01-05)()
- DOI：10.3788/OPE.20152313.0713
  中图分类号： TP391.4
- 收稿日期：2015-06-05，
  
  修回日期：2015-06-21，
  
  纸质出版日期：2015-11-14
- 稿件说明：
移动端阅览
梁华刚, 孙小喃, 茹锋. 基于两视点的任意虚拟视点图像合成[J]. 光学精密工程, 2015,23(10z): 712-721

LIANG Hua-gang, SUN Xiao-nan, RU Feng. Image synthesis of arbitrary virtual viewpoint based on two viewpoints[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10z): 712-721
梁华刚, 孙小喃, 茹锋. 基于两视点的任意虚拟视点图像合成[J]. 光学精密工程, 2015,23(10z): 712-721 DOI： 10.3788/OPE.20152313.0713.

LIANG Hua-gang, SUN Xiao-nan, RU Feng. Image synthesis of arbitrary virtual viewpoint based on two viewpoints[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10z): 712-721 DOI： 10.3788/OPE.20152313.0713.

摘要

针对虚拟视点图像合成精度和任意虚拟视点的可移动范围受限问题

提出了一种基于两视点的任意虚拟视点图像合成方法。考虑各视点图像间的射影几何关系

对视点位置进行了合理布设

建立了简化坐标系模型

推导出了空间中任意虚拟视点图像与两输入视点图像上对应点之间的几何关系。对各视点图像进行了特征点提取、对应关系匹配、视图平行化、三角网格化、纹理粘贴、逆透视投影变换等处理

结合两输入视点与任意虚拟视点之间的位置比率参数

生成了任意虚拟视点图像。实验结果表明

本文方法既避免了繁杂的三维重建及相机强标定

又解决了传统View Morphing技术的虚拟视点移动范围局限问题

仅利用虚拟视点与两输入视点间的位置比率参数即可生成空间中没有不自然感的大范围任意移动的虚拟视点图像;即使输入视点图像无法完全平行化

本文方法依然合理有效

可进一步应用到多视点图像合成等领域。

Abstract

The synthesis precision of an arbitrary virtual viewpoint image and the movement range of a virtual viewpoint were mainly studied. A novel and effective method to synthesize a new arbitrary virtual viewpoint image based on two images was proposed. The simplified model of the viewpoint images was established in a proper coordinate system to analyze the projective geometry relationship of the corresponding points between the input viewpoint images and the arbitrary virtual viewpoint image. Each image was processed by the feature point extraction

correspondence matching and view parallel

triangular segmentation

texture matching

perspective projection transformation. An arbitrary virtual view image was generated in the space only using the positional ratio parameters between input viewpoints and virtual viewpoint. Using this method

complex three-dimensional reconstruction and camera calibration are avoided

and the limitation of the movement range of the virtual viewpoint based on traditional View Morphing technology also is solved. The experiments and simulation results show that the arbitrary virtual viewpoint images can be obtained only using the positional ratio parameters between input viewpoints and virtual viewpoint through the method proposed in this paper

even if the two input images can't be parallel completely. The proposed method is reasonable and effective.

关键词

Keywords

references

WOLBERG Q. Image morphing:a survey[J].The Visual Computer, 1998,14(8):360-372.

SMOLIC A, FEHN C, MÜLLER K,et al.. MPEG 3DAV-video-based rendering for interactive TV application[C]. Proceedings of the 10th Dortumnder Fernsehsemiar, Dortnmnd, 2003:183-188.

SMOLIC A, KAUFF P. Interactive 3D Video Representation and Coding technologies[J]. Proceedings of the IEEE, Special Issue on Advances in Video Coding and Delivery, 2005,93(1):99-110.

SAITO H,BABA S,KANADE T. Appearance-based virtual generation from multicamera video captured in the 3-D Room[J]. IEEE Multimedia, 2003,5(3):303-316.

SHUM H Y,KANG S B. A review of image-based rendering techniques[C]. IEEE/SPIE Visual Comunications and Processing(VCIP), Perth, 2000:2-13.

刘然,朱庆生,易琳,等. 基于图像重投影的视图合成[J]. 计算机应用, 2010,30(4):898-901. LIU R, ZHU Q SH, YI L, et al.. View synthesis based on image reprojection[J]. Journal of Computer Applications, 2010,30(4):898-901.(in Chinese)

KYOUNGSU O, HYOWON K, CHULHAN L,et al.. Real-time rendering of multi-view images from a single image with depth[C]. Proceedings of the 5th International Conference on Computational Science and Applications, Washington, DC:IEEE Computer Society, 2007:505-509.

BEIER T, NEELY S. Feature-based image metamorphosis[J]. Computer Graphics(SIGGRAPH'92), 1992(26):35-42.

CHEN S E, WILLIAMS L. View interpolation for image synthesis[J]. Computer Graphics(SIGGRAPH'93), 1993:279-288.

FUCHS H, BISHOP G, ATHUR K, et al.. Virtual space teleconferencing using a sea of cameras[J]. In First International Symposium on Medical Robotics and Computer Assisted Surgery, 1994:161-167.

HAVALDAR P, LEE MS, MEDIONI G. Synthesizing novel views from unregistered 2-D images[J]. Computer Graphics Forum, 1997,16(l):65-73.

FAUGERAS O, LAVEAU S,ROBERT L,et al.. 3-D reconstruction of urban scenes from sequences of images[J]. Computer Vision and Image Understanding,1998,69(3):292-309.

CHEN S E, WILLIAMS L. View interpolation for image synthesis[J]. Computer Graphics(SIGGRAPH'93), 1993:279-288.

SEITZ S M,DYER C R. View Morphing[J]. Proceedings of SIGGRAPH'96,1996:21-31.

XIAO J J, SHAH M. From images to video:view morphing of three images[C]. Conference on Vision, Modeling and Visualization,2003:495-502.

HARTLEY R, Zisserman. Multiple View Geometry in Computer Vision[M]. Cambridge:Cambridge University Press, United Kingdom, 2000.

浏览量

620

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

应用抛物线运动估计摄像机姿态

LightDiffu-DCE：基于光照强度扩散的低光照图像增强

多级图特征融合引导相机位姿回归

基于机载的红外动态目标视频实时超分辨率重建

基于知识蒸馏的Transformer视觉跟踪器