Accurate, Dense, and Robust Multiview Stereopsis

This paper proposes a novel algorithm for multiview stereopsis that outputs a dense set of small rectangular patches covering the surfaces visible in the images. Stereopsis is implemented as a match, expand, and filter procedure, starting from a sparse set of matched keypoints, and repeatedly expand...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on pattern analysis and machine intelligence Ročník 32; číslo 8; s. 1362 - 1376
Hlavní autoři:	Furukawa, Yasutaka, Ponce, Jean
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Los Alamitos, CA IEEE 01.08.2010 IEEE Computer Society The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	3D/stereo scene analysis Algorithms Applied sciences Artificial intelligence Benchmark testing Buildings Computer science; control theory; systems Computer vision Consistency Exact sciences and technology Image motion analysis Image reconstruction Intelligence Layout Matched filters Mathematical models modeling and recovery of physical attributes motion Motion analysis Obstacles Pattern recognition. Digital image processing. Computational geometry Photometry Robustness shape Solid modeling Studies Visibility Initialization Computer vision Stereo image processing motion shape Outdoor installation Crowd Silhouette Modeling 3D/stereo scene analysis Outlier Multiple view Computational geometry Matched filter Scene analysis Sparse set Visible spectrum Visibility Stereopsis Pattern analysis Artificial intelligence Photometry modeling and recovery of physical attributes
ISSN:	0162-8828, 1939-3539, 1939-3539
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!