Perceiving dynamic scenes of rigid bodies, through affine projections of moving 3D point clouds, boils down to clustering the rigid motion subspaces supported by the points' ...
Most interactive segmentation methods are defined at a 2-d level requiring sometimes extensive interaction when the object of interest is difficult to be outlined by simple means ...
In this work, we propose an unsupervised Bayesian model for the detection of moving objects from dynamic scenes. This unsupervised solution is a three-step approach that uses a st...
We propose a geometric approach to 3D motion segmentation from point correspondences in three perspective views. We demonstrate that after applying a polynomial embedding to the po...
This paper presents a complete system capable of synthesizing a large number of pixels that are missing due to occlusion or damage in an uncalibrated input video. These missing pix...
Jiaya Jia, Yu-Wing Tai, Tai-Pang Wu, Chi-Keung Tan...