Lumiproxy:A Hybrid Representation of Image-Based Models  

作　　者：盛斌 朱鉴 吴恩华 张言辞 

机构地区：[1]Department of Computer Science and Engineering,The Chinese University of Hong Kong [2]Faculty of Science and Technology,University of Macao [3]Institute of Software,Chinese Academy of Sciences [4]Department of Informatics,University of Zurich

出　　处：《Journal of Computer Science & Technology》2009年第3期578-587,共10页计算机科学技术学报（英文版）

基　　金：Supported by the National Basic Research 973 Program of China under Grant No.2009CB320802;the National High-Tech Research and Development 863 Program of China under Grant No.2008AA01Z301;the National Natural Science Foundation of Chinaunder Grant No.60833007;the Research Grant from University of Macao,RGC Research Grant (Ref.416007);UGC Direct Grant(No.2050349)

摘　　要：In this paper, we present a hybrid representation of image-based models combining the textured planes and the hierarchical points. Taking a set of depth images as input, our method starts from classifying input pixels into two categories, indicating the planar and non-planar surfaces respectively. For the planar surfaces, the geometric coefficients are reconstructed to form the uniformly sampled textures. For nearly planar surfaces, some textured planes, called lumiproxies, are constructed to represent the equivalent visual appearance. The Hough transform is used to find the positions of these textured planes, and optic flow measures are used to determine their textures. For remaining pixels corresponding to the non-planar geometries, the point primitive is applied, reorganized as the OBB-tree structure. Then, texture mapping and point splatting are employed together to render the novel views, with the hardware acceleration.In this paper, we present a hybrid representation of image-based models combining the textured planes and the hierarchical points. Taking a set of depth images as input, our method starts from classifying input pixels into two categories, indicating the planar and non-planar surfaces respectively. For the planar surfaces, the geometric coefficients are reconstructed to form the uniformly sampled textures. For nearly planar surfaces, some textured planes, called lumiproxies, are constructed to represent the equivalent visual appearance. The Hough transform is used to find the positions of these textured planes, and optic flow measures are used to determine their textures. For remaining pixels corresponding to the non-planar geometries, the point primitive is applied, reorganized as the OBB-tree structure. Then, texture mapping and point splatting are employed together to render the novel views, with the hardware acceleration.

关 键 词：lumiproxy sampling surface fitting image-based rendering 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]