Sparse GPU Voxelization for 3D Surface Reconstruction

作者: Charles T. Loop

DOI:

关键词:

摘要: Processes and systems described herein enable a computing device to perform voxel-based three-dimensional (3D) reconstruction modeling using parallel graphics hardware. The may generate an initial low resolution voxel list. voxels of the list be represented as index triples corresponding 3D spatial location cell within grid (e.g., {ix,iy,iz}). Based on information input images associated with object, remove certain that do not intersect surface object. remaining subdivided one or more times into number sub-voxels in new newly generated tested again determine object surface. This process repeat part. output rendered projected images.

参考文章(72)
Ji-Hyung Lee, Seung-wook Lee, Bon-Ki Koo, Ho-Won Kim, Apparatus and method for estimating joint structure of human body ,(2013)
Martin Granger-Piché, Emric Epstein, Pierre Poulin, Interactive Hierarchical Space Carving with Projector-based Calibrations vision modeling and visualization. pp. 159- 166 ,(2004)
Martin Karlsson, Shailender Chaudhry, Paul Caprioli, Index generation for cache memories ,(2012)
Yury Y. Uralsky, Jerome F. Duluk, David Luebke, Henry Packard Moreton, Eric Enderton, Eric B. Lum, Cyril Crassin, Generating anti-aliased voxel data ,(2013)
Xavier Décoret, Elmar Eisemann, Single-pass GPU solid voxelization for real-time applications graphics interface. pp. 73- 80 ,(2008)
Giles Roger Frazier, Richard Louis Arndt, Assist Thread Analysis and Debug Mechanism ,(2012)
Fabrice Neyret, Samuel Hornus, Sylvain Lefebvre, Octree Textures on the GPU Addison Wesley. ,(2005)
Alexander Schick, Rainer Stiefelhagen, Real-Time GPU-Based Voxel Carving with Systematic Occlusion Handling joint pattern recognition symposium. ,vol. 5748, pp. 372- 381 ,(2009) , 10.1007/978-3-642-03798-6_38