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. 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.
Original language | English (US) |
---|---|
Pages (from-to) | 722-729 |
Number of pages | 8 |
Journal | Proceedings of the IEEE International Conference on Computer Vision |
Volume | 2 |
DOIs | |
State | Published - 1999 |
Event | Proceedings of the 1999 7th IEEE International Conference on Computer Vision (ICCV'99) - Kerkyra, Greece Duration: Sep 20 1999 → Sep 27 1999 |
All Science Journal Classification (ASJC) codes
- Software
- Computer Vision and Pattern Recognition