We develop an optical flow estimation framework that focuses on motion estimation over time formulated in a Dynamic Bayesian Network. It realizes a spatiotemporal integration of ...
Volker Willert, Marc Toussaint, Julian Eggert, Edg...
The accuracy of optical flow estimation algorithms has been improving steadily as evidenced by results on the Middlebury optical flow benchmark. The typical formulation, however...
We discuss the cause of a severe optical flow estimation problem that fine motion structures cannot always be correctly reconstructed in the commonly employed multiscale variati...
In this paper, we address the topic of estimating two-frame dense optical flow from the monogenic curvature tensor. The monogenic curvature tensor is a novel image model, from whi...
Di Zang, Lennart Wietzke, Christian Schmaltz, Gera...
We propose a principled framework to model persistent motion in dynamic scenes. In contrast to previous efforts on object tracking and optical flow estimation that focus on local...