Variational Light Field Analysis for Disparity Estimation and Super-Resolution

We develop a continuous framework for the analysis of 4D light fields, and describe novel variational methods for disparity reconstruction as well as spatial and angular super-resolution. Disparity maps are estimated locally using epipolar plane image analysis without the need for expensive matching...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on pattern analysis and machine intelligence Ročník 36; číslo 3; s. 606 - 619
Hlavní autoři: Wanner, Sven, Goldluecke, Bastian
Médium: Journal Article
Jazyk:angličtina
Vydáno: Los Alamitos, CA IEEE 01.03.2014
IEEE Computer Society
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
3D reconstruction
Algorithms
Applied sciences
Artificial intelligence
Cameras
Computer science; control theory; systems
Cost analysis
Discretization
epipolar plane images
Estimation
Exact sciences and technology
Geometry
Image reconstruction
Light fields
Optimization
Pattern recognition. Digital image processing. Computational geometry
Reconstruction
Source code
Spatial resolution
super-resolution
Tensile stress
Variational methods
view interpolation
epipolar plane images
Cost minimization
High resolution
Angular resolution
Image processing
super-resolution
Image reconstruction
variational methods
3D reconstruction
Discretization
Information source
Variational calculus
Light fields
Stereopsis
Mathematical programming
Computer vision
Real number
view interpolation
Inverse problem
Image analysis
Sampling rate
Tridimensional image
Data field
Disparity
Spatial resolution
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We develop a continuous framework for the analysis of 4D light fields, and describe novel variational methods for disparity reconstruction as well as spatial and angular super-resolution. Disparity maps are estimated locally using epipolar plane image analysis without the need for expensive matching cost minimization. The method works fast and with inherent subpixel accuracy since no discretization of the disparity space is necessary. In a variational framework, we employ the disparity maps to generate super-resolved novel views of a scene, which corresponds to increasing the sampling rate of the 4D light field in spatial as well as angular direction. In contrast to previous work, we formulate the problem of view synthesis as a continuous inverse problem, which allows us to correctly take into account foreshortening effects caused by scene geometry transformations. All optimization problems are solved with state-of-the-art convex relaxation techniques. We test our algorithms on a number of real-world examples as well as our new benchmark data set for light fields, and compare results to a multiview stereo method. The proposed method is both faster as well as more accurate. Data sets and source code are provided online for additional evaluation.
Bibliografie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0162-8828
1939-3539
2160-9292
1939-3539
DOI:10.1109/TPAMI.2013.147