Abstract
We address the problem of efficient structure from motion for large, unordered, highly redundant, and irregularly sampled photo collections, such as those found on Internet photo-sharing sites. Our approach computes a small skeletal subset of images, reconstructs the skeletal set, and adds the remaining images using pose estimation. Our technique drastically reduces the number of parameters that are considered, resulting in dramatic speedups, while provably approximating the covariance of the full set of parameters. To compute a skeletal image set, we first estimate the accuracy of two-frame reconstructions between pairs of overlapping images, then use a graph algorithm to select a subset of images that, when reconstructed, approximates the accuracy of the full set. A final bundle adjustment can then optionally be used to restore any loss of accuracy.
Keywords
Bundle adjustmentComputer scienceSet (abstract data type)GraphArtificial intelligenceCovarianceComputer visionIterative reconstructionAlgorithmStructure from motionMotion estimationFrame (networking)Image (mathematics)Pattern recognition (psychology)MathematicsTheoretical computer science
Affiliated Institutions
Related Publications
Active appearance models
We describe a new method of matching statistical models of appearance to images. A set of model parameters control modes of shape and gray-level variation learned from a trainin...
Motion-Compensated Television Coding: Part I
We present methods of estimating displacements of moving objects from one frame to the next in a television scene and using such displacements for frame-to-frame prediction. Dis...
Normalized cuts and image segmentation
We propose a novel approach for solving the perceptual grouping problem in vision. Rather than focusing on local features and their consistencies in the image data, our approach...
Ambient Occlusion and Edge Cueing for Enhancing Real Time Molecular Visualization
The paper presents a set of combined techniques to enhance the real-time visualization of simple or complex molecules (up to order of 106 atoms) space fill mode. The proposed ap...
A general framework for object detection
This paper presents a general trainable framework for object detection in static images of cluttered scenes. The detection technique we develop is based on a wavelet representat...
Publication Info
- Year
- 2008
- Type
- article
- Pages
- 1-8
- Citations
- 268
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
268
OpenAlex
Cite This
Noah Snavely,
Steven M. Seitz,
Richard Szeliski
(2008).
Skeletal graphs for efficient structure from motion.
, 1-8.
https://doi.org/10.1109/cvpr.2008.4587678
Identifiers
- DOI
- 10.1109/cvpr.2008.4587678