View Synthesis using Convex and Visual Hulls

This paper discusses two efficient methods for image based rendering. Both algorithms approximate the world object. One uses the convex hull and the other uses the visual hull. We show that the overhead of using the latter is not always justified and in some cases, might even hurt. We demonstrate the method on real images from a studio-like setting in which many cameras are used, after a simple calibration procedure. The novelties of this paper include showing that projective calibration suffices for this computation and providing simpler formulation that is base only on image measurements.

[1]  R. Zabih,et al.  Exact voxel occupancy with graph cuts , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[2]  Paul Debevec,et al.  Modeling and Rendering Architecture from Photographs , 1996, SIGGRAPH 1996.

[3]  Andrew Zisserman,et al.  Surface Reconstruction from Multiple Views Using Apparent Contours and Surface Texture , 2000, Confluence of Computer Vision and Computer Graphics.

[4]  Andrew W. Fitzgibbon,et al.  Automatic 3D Model Construction for Turn-Table Sequences , 1998, SMILE.

[5]  Amnon Shashua,et al.  Novel view synthesis in tensor space , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Takeo Kanade,et al.  Virtualized Reality: Constructing Virtual Worlds from Real Scenes , 1997, IEEE Multim..

[7]  A. Laurentini,et al.  The Visual Hull Concept for Silhouette-Based Image Understanding , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Ramesh Raskar,et al.  Image-based visual hulls , 2000, SIGGRAPH.

[9]  Larry S. Davis,et al.  A Robust Background Subtraction and Shadow Detection , 1999 .

[10]  Amnon Shashua,et al.  Threading Fundamental Matrices , 1998, ECCV.

[11]  Richard Szeliski,et al.  Rapid octree construction from image sequences , 1993 .