GPU-Based Optimization of a Free-Viewpoint Video System
Orman, Neal (Worcester Polytechnic Institute (Worcester, Estats Units d'Amèrica). Computer Science Department)
Kim, Hansung (Advanced Telecommunications Research Institute International (Kyoto Japó). Knowledge Science Lab)
Sakamoto, Ryuuki (Advanced Telecommunications Research Institute International (Kyoto Japó). Knowledge Science Lab)
Toriyama, Tomoji (Advanced Telecommunications Research Institute International (Kyoto Japó). Knowledge Science Lab)
Kogure, Kiyoshi (Advanced Telecommunications Research Institute International (Kyoto Japó). Knowledge Science Lab)
Lindeman, Robert (Worcester Polytechnic Institute (Worcester, Estats Units d'Amèrica). Computer Science Department)

Data:	2008
Resum:	We present a method for optimizing the reconstruction and rendering of 3D objects from multiple images by utilizing the latest features of consumer-level graphics hardware based on shader model 4. 0. We accelerate visual hull reconstruction by rewriting a shape-from-silhouette algorithm to execute on the GPU's parallel architecture. Rendering a is optimized through the application of geometry shaders to generate billboarding microfacets textured with captured images. We also present a method for handling occlusion in the camera selection process that is optimized for execution on the GPU. Execution time is further improved by rendering intermediate results directly to texture to minimize the number of data transfers between graphics and main memory. We show our GPU based system to be significantly more efficient than a purely CPU-based approach, due to the parallel nature of the GPU, while maintaining graphical quality.
Drets:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial i la comunicació pública de l'obra, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. No es permet la creació d'obres derivades.
Llengua:	Anglès
Document:	Article ; recerca ; Versió publicada
Matèria:	Reconstrucció en 3D ; Modelat i reproducció basats en l'imatge ; Reconstrucción en 3D ; Modelado y reproducción basada en la imagen ; 3D Reconstruction ; GPGPU ; Image-Based Modeling and Rendering ; Microfacet Billboarding
Publicat a:	ELCVIA : Electronic Letters on Computer Vision and Image Analysis, V. 7 n. 2 (2008) p. 120-133, ISSN 1577-5097

Adreça original: https://elcvia.cvc.uab.es/article/view/v7-n2-orman-kim-sakamoto-et-al
Adreça alternativa: https://raco.cat/index.php/ELCVIA/article/view/132007
DOI: 10.5565/rev/elcvia.180

13 p, 370.1 KB

El registre apareix a les col·leccions:
Articles > Articles publicats > ELCVIA
Articles > Articles de recerca