Real-time view synthesis from a sparse set of views
作者： George Chen , Yang Liu , Nelson Max
DOI: 10.1016/J.IMAGE.2006.12.003
关键词:
摘要: It is known that the pure light field approach for view synthesis relies on a large number of image samples to produce anti-aliased renderings. Otherwise, insufficiency sampling needs be compensated by geometry sampling. Currently, estimation done either offline or using dedicated hardware. Our solution this dilemma based three key ideas: formal analysis equivalency between rendering and plane-based warping, multi focus imaging in camera system plane sweeping, fusion stereo. The essence our method perform necessary depth up level required minimal joint image-geometry rate off-the-shelf graphics As result, real-time achieved even if are insufficient.
acm.org
elsevier.com
sci-hub.se 参考文章(28)
Emilio Camahort, Apostolos Lerios, Donald Fussell, Uniformly Sampled Light Fields eurographics. pp. 117- 130 ,(1998) , 10.1007/978-3-7091-6453-2_11
Richard Hartley, Andrew Zisserman, Multiple View Geometry ,(1999)
B. Heigl, R. Koch, M. Pollefeys, J. Denzler, L. Van Gool, Plenoptic Modeling and Rendering from Image Sequences Taken by Hand-Held Camera Mustererkennung 1999, 21. DAGM-Symposium. pp. 94- 101 ,(1999) , 10.1007/978-3-642-60243-6_11
J. P. Grossman, William J. Dally, Point Sample Rendering eurographics. pp. 181- 192 ,(1998) , 10.1007/978-3-7091-6453-2_17
Richard Hartley, Andrew Zisserman, Multiple view geometry in computer visiond Cambridge University Press. ,(2001)
George Q. Chen, Gérard G. Medioni, Practical algorithms for stratified structure-from-motion Image and Vision Computing. ,vol. 20, pp. 103- 123 ,(2002) , 10.1016/S0262-8856(01)00090-7
T. Kanade, P. Rander, P.J. Narayanan, Virtualized reality: constructing virtual worlds from real scenes IEEE MultiMedia. ,vol. 4, pp. 34- 47 ,(1997) , 10.1109/93.580394
Marc Levoy, Pat Hanrahan, Light field rendering international conference on computer graphics and interactive techniques. pp. 31- 42 ,(1996) , 10.1145/237170.237199
S. Baker, T. Sim, T. Kanade, When is the shape of a scene unique given its light-field: a fundamental theorem of 3D vision? IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 25, pp. 100- 109 ,(2003) , 10.1109/TPAMI.2003.1159949
C. Lawrence Zitnick, Sing Bing Kang, Matthew Uyttendaele, Simon Winder, Richard Szeliski, High-quality video view interpolation using a layered representation ACM Transactions on Graphics. ,vol. 23, pp. 600- 608 ,(2004) , 10.1145/1015706.1015766