Piecewise Image Registration in the Presence of Multiple Large Motions

Authors:
Pravin Bhat;Ke Colin Zheng;Noah Snavely;Aseem Agarwala;Maneesh Agrawala;Michael F. Cohen;Brian Curless
Affiliations:
University of Washington, USA;University of Washington, USA;University of Washington, USA;University of Washington, USA;University of California, Berkeley, USA;Microsoft Research, USA;University of Washington, USA
Venue:
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Year:
2006

Citing 0
Cited 7

Generation of a disparity map using piecewise linear transformation

CIMMACS'06 Proceedings of the 5th WSEAS International Conference on Computational Intelligence, Man-Machine Systems and Cybernetics
Bayesian optimization of the scale saliency filter

Image and Vision Computing
Noisy video super-resolution

MM '08 Proceedings of the 16th ACM international conference on Multimedia
Simultaneous plane extraction and 2D homography estimation using local feature transformations

ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part II
Video completion for indoor scenes

ICVGIP'06 Proceedings of the 5th Indian conference on Computer Vision, Graphics and Image Processing
Using photographs to enhance videos of a static scene

EGSR'07 Proceedings of the 18th Eurographics conference on Rendering Techniques
Landmark-based non-rigid registration via graph cuts

ICIAR'07 Proceedings of the 4th international conference on Image Analysis and Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a technique for computing a dense pixel correspondence between two images of a scene containing multiple large, rigid motions. We model each motion with either a homography (for planar objects) or a fundamental matrix. The various motions in the scene are first extracted by clustering an initial sparse set of correspondences between feature points; we then perform a multi-label graph cut optimization which assigns each pixel to an independent motion and computes its disparity with respect to that motion. We demonstrate our technique on several example scenes and compare our results with previous approaches.