期刊文献+

高质量的虚拟视点图像的绘制方法 被引量:8

Virtual View Image Rendering with High Quality
下载PDF
导出
摘要 针对应用深度图像的绘制(DIBR)技术生成的虚拟视点图像中存在的空洞问题,提出了一种基于DIBR的高质量的虚拟视点图像绘制算法。先由多幅参考图像分别生成同一虚拟视点位置的多幅目标图像,将这些虚拟视点目标图像融合为含有少量空洞的目标图像,然后采用逆映射的方法在多幅参考图像中找到这些剩余少量空洞的对应内容并填充空洞,从而生成高质量的虚拟视点图像。实验结果表明最后生成的虚拟视点图像具有良好的视觉效果。 According to the hole problem appearing in virtual view images, a new virtual view images with high image quality rendering algorithm based on Depth Image Based Rendering (DIBR) is proposed. Firstly, several images of the same virtual viewpoint are created by multiple reference images, and these virtual view images are merged into one target image with fewer holes. Then the correspondences in multi-reference images for those remaining holes are found to fill the holes by inverse warping, and a virtual view image with high quality is generated finally. Experimental results show that the generated virtual view images have favorite view effect.
出处 《电视技术》 北大核心 2009年第9期9-11,25,共4页 Video Engineering
基金 国家自然科学基金项目(60832003 60672052) 上海市曙光计划项目(06SG43) 上海市产学研示范工程项目(07-040C)
关键词 基于深度图像的绘制 虚拟视点图像 逆映射 DIBR virtual viewpoint image inverse warping
  • 相关文献

参考文献8

  • 1MCMILLAN L. An image-based approach to three-dimensional computer graphics [D]. NC,USA:University of North Carolina at Chapel Hill, 1997.
  • 2FEHN C A. 3D-TV approach using depth-image-based rendering (DIBR)[C]//Proc. Visualization,Imaging,and Image Processing ' 03. Benalmadena,Spain : [s.n.], 2003:482-487.
  • 3SHADE J,GORTLER S,HE L W, et al. Layered depth images[C] //Proc. ACM SIGGRAPH' 98. Orlando:[s.n.],1998:231-242.
  • 4ZHANG Limlg,TAM W J. Slereoscopic image generation based on depth images for 3DTV[J].IEEE Trans. Broadcasting,2005,51 (2): 191-199.
  • 5CHEN W Y,CHANG Y L,LIN S F,et al. Efficient depth image based rendering with edge dependent depth filter and interpolation [C]//Proc. ICME 2005. [S.l.]:IEEE Press,2005:1314-1317.
  • 6JUNG K H,PARK Y K,KIM J K,et al. Depth image based rendering for 3D data services over T-DMB [C]//Proc. IEEE 3DTV- CON' 08. Istanbul,Turkey:[s.n.],2008:28-30.
  • 7MCMILLAN L. A list-priority rendering algorithm for redisplaying projected surfaces [D]. NC,USA:University of North Carolina at Chapel Hill, 1995.
  • 8MARCATO R W. Optimizing an inverse warper [D]. Boston:MIT, 1998.

同被引文献56

  • 1赵岩,汪敬媛,陈贺新,刘静,王珂玮.基于深度图像和半像素的虚拟视点绘制[J].吉林大学学报(工学版),2013,43(S1):256-259. 被引量:4
  • 2黄文辉,陈仁雷,张家谋.数字视频图像质量客观测量方法的改进与实现[J].北京邮电大学学报,2005,28(4):87-90. 被引量:26
  • 3KUBOTA A,SMOLIC A,MAGNOR M,et al. Muhiview imaging and 3DTV[J]. IEEE Signal Processing Magazine,2007,24(6):10-21.
  • 4MATUSIK W,PFISTER H. 3DTV: a scalable system for real-time acquisition, transmission and autostereoscopic display of dynamic scenes[EB/OL]. [2009-03-01.] http://people.csail.mit.edu/wojciech/ 3DTV/3DTV.pdf.
  • 5CHEN Wan yu,CHANG Yu lin,LIN S F,et al. Efficient depth image based rendering with edge dependent depth filter and interpolation[C]//Proc. IEEE International Conference on Multimedia and Expo, 2005(ICME 2005). [S.l.]:IEEE Press , 2005 :1314-1317.
  • 6ZHANG C,CHEN T. A survey on image-based rendering- representation, sampling, and compression[J]. Signal Processing: Image Communication, 2004,19 ( 1 ) : 1-28.
  • 7CHENG C,LI C,CHEN L A 2D-to-3D conversion system using edge in- formation[ C]//2010 Digest of Technical Papers International Conference on Consumer Electronics. [ S. l. ] :IEEE Press,2010:377-378.
  • 8BATTIATO S,CURTI S,CASCIA M L,et al. Depth map generation by im- age classification[ C ]//Proc. SPIE:vol. 5302. [ S. l. ] :SPIE Press ,2004 : 95-104.
  • 9BATTIATO S,CAPRA A,CURTI S,et al. 3D stereoscopic image pairs by depth- map generation [ EB/OL ] . [ 2010 - 04 - 01 ] . http://cgit. nutn. edu. tw :8080/cgit/PaperDL/WSY_100506083318. PDF.
  • 10JUNG J ,HO Y. Depth map estimation from single-view image using object classification based on Bayesian learning [ C ]//3 DTV- Conference: The True Vision - Capture,Transmission and Display of 3D Video. [ S. 1. ] : IEEE Press,2010 : 1-4.

引证文献8

二级引证文献14

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部