Match Propagation for Image-Based Modeling and Rendering

Autor: Maxime Lhuillier, Long Quan
Přispěvatelé: Laboratoire des sciences et matériaux pour l'électronique et d'automatique (LASMEA), Université Blaise Pascal - Clermont-Ferrand 2 (UBP)-Centre National de la Recherche Scientifique (CNRS), Vision and Graphics Laboratory (VISGRAPH), Hong Kong University of Science and Technology (HKUST), Ballet, Pascale, Lhuillier, Maxime
Jazyk: angličtina
Rok vydání: 2002
Předmět:
Computer science
[SPI] Engineering Sciences [physics]
02 engineering and technology
image-based modeling and rendering
Rendering (computer graphics)
[SPI]Engineering Sciences [physics]
[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
Artificial Intelligence
0202 electrical engineering
electronic engineering
information engineering
Computer vision
Tiled rendering
Blossom algorithm
occlusions
business.industry
quasi-dense matching
Applied Mathematics
Template matching
[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
020207 software engineering
Image-based modeling and rendering
stereo vision
Real-time rendering
Visualization
Computational Theory and Mathematics
020201 artificial intelligence & image processing
Computer Vision and Pattern Recognition
Artificial intelligence
Alternate frame rendering
business
Algorithm
Software
Zdroj: IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24, p. 1140-1146
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, pp.1146
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2002, pp.1146
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2002, 24, p. 1140-1146
ISSN: 0162-8828
Popis: International audience; This paper presents a quasi-dense matching algorithm between images based on match propagation principle. The algorithm starts from a set of sparse seed matches, then propagates to the neighboring pixels by the best-first strategy, and produces a quasi-dense disparity map. The quasi-dense matching aims at broad modeling and visualization applications which rely heavily on matching information. Our algorithm is robust to initial sparse match outliers due to the best-first strategy; It is efficient in time and space as it is only output sensitive; It handles half-occluded areas because of the simultaneous enforcement of newly introduced discrete 2D gradient disparity limit and the uniqueness constraint. The properties of the algorithm are discussed and empirically demonstrated. The quality of quasi-dense matching are validated through intensive real examples.
Databáze: OpenAIRE
Externí odkaz: