Linear view synthesis using a dimensionality gap light field prior
Name
Durand-Linear view synthesis.pdf
Size
598.95 KB
Format
Adobe PDF
Checksum (MD5)
0443577d860325c4fc3cf3523275a9bf
Author(s)
Levin, Anat
Durand, Fredo
Date Issued
August 2010
Journal
IEEE Conference Computer Vision and Pattern Recognition 2010 (CVPR)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Levin, Anat, and Fredo Durand. “Linear View Synthesis Using a Dimensionality Gap Light Field Prior.” IEEE Conference Computer Vision and Pattern Recognition 2010 (CVPR). 1831–1838. © Copyright 2010 IEEE
Version
Final published version
Abstract
Acquiring and representing the 4D space of rays in the world (the light field) is important for many computer vision and graphics applications. Yet, light field acquisition is costly due to their high dimensionality. Existing approaches either capture the 4D space explicitly, or involve an error-sensitive depth estimation process. This paper argues that the fundamental difference between different acquisition and rendering techniques is a difference between prior assumptions on the light field. We use the previously reported dimensionality gap in the 4D light field spectrum to propose a new light field prior. The new prior is a Gaussian assigning a non-zero variance mostly to a 3D subset of entries. Since there is only a low-dimensional subset of entries with non-zero variance, we can reduce the complexity of the acquisition process and render the 4D light field from 3D measurement sets. Moreover, the Gaussian nature of the prior leads to linear and depth invariant reconstruction algorithms. We use the new prior to render the 4D light field from a 3D focal stack sequence and to interpolate sparse directional samples and aliased spatial measurements. In all cases the algorithm reduces to a simple spatially invariant deconvolution which does not involve depth estimation.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/CVPR.2010.5539854
