Temporal Alignment of 3D Video Sequences Using Shape and Appearance
Temporal Alignment of 3D Video Sequences Using Shape and Appearance
复制标题
DOI：
10.1109/cvmp.2010.22
复制
发表时间：
2010-11
期刊：
影响因子：
--
通讯作者：
C. Budd;A. Hilton
中科院分区：
文献类型：
--
作者：
C. Budd;A. Hilton
在本文中，我们提出了一种方法来自动引入时间一致性到一系列的网格重建从多视点视频。我们联合收割机的一些优点，以前的工作，产生一个强大的算法。我们的方法使用SIFT特征在每个相机视图结合几何信息，以产生准确的帧到帧的对应关系。将其与体积和表面拉普拉斯变形技术相结合，我们能够在3D视频序列中变形良好的重建帧。虽然该方法是顺序的，但外观和形状匹配的组合允许从先前帧或表面重建中的错误中恢复。
In this paper we present a method to automatically introduce temporal consistency into a sequence of meshes reconstructed from multi-view video. We combine a number of advantages of previous work to produce a robust algorithm. Our approach uses SIFT features in each camera view combined with geometric information to produce accurate frame to frame correspondence. Coupling this with both volumetric and surface laplacian deformation techniques we are able to deform a well reconstructed frame across the 3D video sequence. Although the approach is sequential the combination of appearance and shape matching allows recovery from errors in previous frames or surface reconstruction.