We present an approach to 3D scene flow estimation, which exploits that in realistic scenarios image motion is frequently dominated by observer motion and independent, but rigid ...
We propose a Bayesian framework for representing and recognizing local image motion in terms of two basic models: translational motion and motion boundaries. Motion boundaries are ...
Abstract— Frequency synchronization is one of the most important components in orthogonal frequency-division multiplexing (OFDM) systems. Recently, the discrete cosine transform ...
Tao Cui, Feifei Gao, Arumugam Nallanathan, Chintha...
We present a novel method for joint reconstruction of both image and motion in positron-emission-tomography (PET). Most other methods separate image from motion estimation: They us...
In this paper we explore a multiple hypothesis approach to estimating rigid motion from a moving stereo rig. More precisely, we introduce the use of Gaussian mixtures to model cor...