3D modeling and rendering from multiple wide-baseline images by match propagation

In this paper, we present a method for modeling a complex scene from a small set of input images taken from widely separated viewpoints and then synthesizing novel views. First, we find sparse correspondences across multiple input images and calibrate these input images taken with unknown cameras. T...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Signal processing. Image communication Ročník 21; číslo 6; s. 506 - 518
Hlavní autoři: Yao, Jian, Cham, Wai-Kuen
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.07.2006
Témata:
Image-based modeling and rendering
Match propagation
Multiple wide-baseline images
Match propagation
Image-based modeling and rendering
Multiple wide-baseline images
ISSN:0923-5965, 1879-2677
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this paper, we present a method for modeling a complex scene from a small set of input images taken from widely separated viewpoints and then synthesizing novel views. First, we find sparse correspondences across multiple input images and calibrate these input images taken with unknown cameras. Then one of the input images is chosen as the reference image for modeling by match propagation. A sparse set of reliably matched pixels in the reference image is initially selected and then propagated to neighboring pixels based on both the clustering-based light invariant photoconsistency constraint and the data-driven depth smoothness constraint, which are integrated into a pixel matching quality function to efficiently deal with occlusions, light changes and depth discontinuity. Finally, a novel view rendering algorithm is developed to fast synthesize a novel view by match propagation again. Experimental results show that the proposed method can produce good scene models from a small set of widely separated images and synthesize novel views in good quality.
Bibliografie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0923-5965
1879-2677
DOI:10.1016/j.image.2006.03.005