Three-dimensional scene flow
- 1 January 1999
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 722-729 vol.2
- https://doi.org/10.1109/iccv.1999.790293
Abstract
Scene flow is the three-dimensional motion field of points in the world, just as optical flow is the two-dimensional motion field of points in an image. Any optical flow is simply the projection of the scene flow onto the image plane of a camera. We present a framework for the computation of dense, non-rigid scene flow from optical flow. Our approach leads to straightforward linear algorithms and a classification of the task into three major scenarios: complete instantaneous knowledge of the scene structure; knowledge only of correspondence information; and no knowledge of the scene structure. We also show that multiple estimates of the normal flow cannot be used to estimate dense scene flow directly without some form of smoothing or regularization.Keywords
This publication has 19 references indexed in Scilit:
- Constructing virtual worlds using dense stereoPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The reconstruction of dynamic 3D structure of biological objects using stereo microscope imagesMachine Vision and Applications, 1997
- Model-Based Joint Motion and Structure Estimation from Stereo ImagesComputer Vision and Image Understanding, 1997
- Unified optical flow field approach to motion analysis from a sequence of stereo imagesPattern Recognition, 1994
- The Incremental Approximation of Nonrigid MotionCVGIP: Image Understanding, 1994
- Performance of optical flow techniquesInternational Journal of Computer Vision, 1994
- Estimation of displacements from two 3D frames obtained from stereoIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992
- Recovery of nonrigid motion and structureIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991
- 3-D motion estimation using a sequence of noisy stereo images: models, estimation, and uniqueness resultsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990
- Maximizing Rigidity: The Incremental Recovery of 3-D Structure from Rigid and Nonrigid MotionPerception, 1984