In these frameworks, templates are constructed using an iterative process of template estimation and alignment, which is often computationally very expensive. Due in part to this shortcoming, most methods compute asingle template for the entire population of images, or a few templates for specific sub-groups of the data.

Recursion is the fundamental paradigm to finitely describe potentially infinite objects.

Each AvehicleC starts sumofcityC, after again.

Estimating the 6D object pose is one of the core problems in computer vision and robotics. It predicts the full configurations of rotation, translation and size of a given object, which has wide applications including Virtual Reality (VR) [2], scene understanding [30], and [42, 57, 31, 49]. There are twodirections in 6D object pose estimation.

We study first-order optimization algorithms for computing the barycenter of Gaussian distributions with respect to the optimal transport metric.

Besides, binarymask has less semantic meanings compared toinstance labels and semantic labels.

We also show that when stochastic mixability does not hold in a certain sense (described in Section 5), then the risk minimizer is not unique in a bad way.