The work proposes a hierarchical architecture for learning amic scenes at various levels of knowledge abstraction. The raw visual information is processed at different stages to g...
We present a solution to the mesh tangling problem in surface tracking. Using an explicit triangle mesh to track the location of a surface as it moves in three dimensions has many ...
We propose a sequential Monte Carlo data association algorithm based on a two-level computational framework for tracking varying number of interacting objects in dynamic scene. Fi...
This paper presents a Bayesian framework for multi-cue 3D object tracking of deformable objects. The proposed spatio-temporal object representation involves a set of distinct linea...
Convex and continuous energy formulations for low level
vision problems enable efficient search procedures for the
corresponding globally optimal solutions. In this work we
exte...
Christopher Zach (UNC Chapel Hill), Marc Niethamme...