Three-dimensional scene flow
- 31 January 2005
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Ieee Transactions On Pattern Analysis and Machine Intelligence
- Vol. 27 (3), 475-480
- https://doi.org/10.1109/tpami.2005.63
Abstract
Just as optical flow is the two-dimensional motion of points in an image, scene flow is the three-dimensional motion of points in the world. The fundamental difficulty with optical flow is that only the normal flow can be computed directly from the image measurements, without some form of smoothing or regularization. In this paper, we begin by showing that the same fundamental limitation applies to scene flow; however, many cameras are used to image the scene. There are then two choices when computing scene flow: 1) perform the regularization in the images or 2) perform the regularization on the surface of the object in the scene. In this paper, we choose to compute scene flow using regularization in the images. We describe three algorithms, the first two for computing scene flow from optical flows and the third for constraining scene structure from the inconsistencies in multiple optical flows.Keywords
This publication has 17 references indexed in Scilit:
- A framework for the robust estimation of optical flowPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Multi-view scene capture by surfel sampling: from video streams to non-rigid 3D motion, shape and reflectancePublished 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
- The Incremental Approximation of Nonrigid MotionComputer Vision and Image Understanding, 1994
- Performance of optical flow techniquesInternational Journal of Computer Vision, 1994
- 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
- Theory for Off-Specular Reflection From Roughened Surfaces*Journal of the Optical Society of America, 1967