期刊文献+

一种基于三角形重投影的虚拟视角合成 被引量:1

Virtual view synthesis based on triangular re-projection
下载PDF
导出
摘要 相比较传统的视角插值合成方法只能在基线上合成虚拟图像,提出的一种基于三角形重投影的虚拟视角合成方法,可以在已知少数几个匹配点的情况下,将场景内容自动迭代划分为一致和非一致三角形区域,通过不同策略的三角形重投影实现更加自由的视点的虚拟图像合成.划分过程中引入直线段约束可以解决直线纹理在三角形接缝处的畸变问题,保证最后的合成图像中场景表示在此处的连续性.利用设计的可信度函数,沿一定搜索路径可找到更多的新匹配点,从而带来更多的一致三角形区域.将此方法应用到虚拟彩色图像的合成,实验结果证明了此方法可以在更大视点范围内合成逼近于真实图的虚拟图像. Traditional view interpolation can only synthesize the novel view along the base line.The proposed method based on triangular re-projection can iteratively divide the scene into consistent and inconsistent triangles given a few of initial matches,and implement free-viewpoint view synthesis by re-projecting these two groups of triangles in different strategies.The straight line constraint was introduced to direct the division along the line in order to reduce the discontinuity nearby the common side of two adjacent triangles.The new matching points were confirmed by the designed evaluation function in a special searching order.They were detected in the inconsistent regions for further division to produce more and more consistent regions.The color-image experiment proves that this method is effective to synthesize a photo-realistic image under wider changes in viewpoint.
作者 张春晓 赵剡
出处 《北京航空航天大学学报》 EI CAS CSCD 北大核心 2012年第1期86-90,共5页 Journal of Beijing University of Aeronautics and Astronautics
基金 中国留学基金委资助项目
关键词 虚拟图像合成 三角形重投影 直线段约束 匹配点 virtual view synthesis triangular re-projection straight line matching points
  • 相关文献

参考文献9

  • 1Ince S,Konrad J.Occlusion-aware view interpolation[J].EURASIP Journal on Image and Video Processing (Special Issue on 3D Image and Video Processing),2008,Article ID 803231,1-15.
  • 2Rogmans S,Lu Jiangbo.Real-time stereo-based view synthesis algorithms:a unified framework and evaluation on commodity GPUs[J].Signal processing:Image Communicati-on.2009,24(1-2):49-64.
  • 3Seitz S M,Dyer C R.Physically-valid view synthesis by image interpolation .Proc Workshop on Representations of Visual Scenes,081867122X,1995.
  • 4Shi Feng,Laganiere R,Dubois E.On the use of ray-tracing for viewpoint interpolation in panoramic imagery //Ferrie F.2009 Canadian Conference on Computer and Robot Vision.Washington DC:IEEE Computer Society,2009:200-207.
  • 5Siu A M K,Lau R W H.Image registration for image-based rendering[J].IEEE Transactions on Image Processing.2005,14(2):241-251.
  • 6Ukita N,Kawata S,Ukita M K.IBR-based free-viewpoint imaging of a complex scene using few cameras //Borgefors G,Flynn P.International Conference on Pattern Recognition.Washington DC:IEEE Computer Society,2008:1-4.
  • 7Faugeras O,Luc R.What can two images tell us about a third one? [J].International Journal of Computer Vision.1996,18(1):5-19.
  • 8Schmid C,Zisserman A.The geometry and matching of lines and curves over multiple views [J].International Journal of Computer Vision.2000,40(3):199-233.
  • 9McMillan L.A list-priority rendering algorithm for redisplaying projected surfaces .UNC-Chapel Hill Computer Science Technical Report,95-005,1995.

同被引文献29

  • 1鲁敏,郁文贤,鲍虎军,匡纲要.基于机电跟踪的三维虚拟演播室系统[J].电子学报,2003,31(z1):2035-2039. 被引量:3
  • 2程文刚,须德,蒋轶玮,即丛妍.一种新的动态视频摘要生成方法[J].电子学报,2005,33(8):1461-1466. 被引量:6
  • 3Pritch Y,Rav-Acha A,Peleg S.Nonchronological video synopsis and indexing[J]. IEEE Trans,2008,PAMI-30(11):1971-1984.
  • 4Y N,C X,H S,et al.Compact video synopsis via global spatiotemporal optimization[J]. IEEE Trans,2013,TVCG-19(10):1664-1676.
  • 5SIMAKOV,D,CASPI,Y,SHECHTMAN,E,AND IRANI,M.Summarizing visual data using bidirectional similarity. Computer Vision and Pattern Recognition[C]. Alaska,USA:IEEE.2008.1-8.
  • 6Nie Y,Sun H,Li P,et al.Object movements synopsis via part assembling and stitching[J]. IEEE Trans,2014,TVCG-20(9):1303-1315.
  • 7Germann M,Popa T,Keiser R,et al.Novel-view synthesis of outdoor sport events using an adaptive view-dependent geometry[J]. Computer Graphics Forum,2012,31(21):325-333.
  • 8Saxena A,Sun M,Ng A Y.Make3D:learning 3D scene structure from a single still image[J]. IEEE Trans,2009,PAMI-31(5):824-840.
  • 9HARTLEY,R,ZISSERMAN,A.Multiple view geometry in computer vision[M]. Cambridge,UK:Cambridge University Press.2003:23-64.
  • 10Maki A,Watanabe M,Wiles C.Geotensity:Combining motion and lighting for 3d surface reconstruction[J]. International Journal of Computer Vision,2002,48(2):75-90.

引证文献1

二级引证文献4

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