S.Vedula, S.Baker, P.Rander, R.Collins and T.Kanade,
"Three-Dimensional Scene Flow,"
International Conference on Computer Vision (ICCV'99),
Corfu, Greece, September 1999, pp.722-729.
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. In this paper, 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: (1) complete instantaneous knowledge of the scene
structure, (2) knowledge only of correspondence information, and (3) 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.
Click here for
full paper (628017 bytes, compressed using gzip).