We describe a method to extract persistent elements of a dynamic scene from an input
video. We represent each scene element as a Deformable Sprite consisting of three …

Models for computer vision are commonly defined either wrt low-level concepts such as
pixels that are to be grouped, or wrt high-level concepts such as semantic objects that are to …

Occlusions play an important role in optical flow and disparity estimation, since matching
costs are not available in occluded areas and occlusions indicate motion boundaries …

The goal of motion segmentation is to segregate a visual scene into independently moving
objects. It is an indispensable pre-processing step for various tasks in computer vision and …

Online unsupervised video object segmentation (UVOS) uses the previous frames as its
input to automatically separate the primary object (s) from a streaming video without using …

We consider the problem of providing dense segmentation masks for object discovery in
videos. We formulate the object discovery problem as foreground motion clustering, where …

Traditional methods of motion segmentation use powerful geometric constraints to
understand motion, but fail to leverage the semantics of high-level image understanding …

Many real-world video sequences cannot be conveniently categorized as general or
degenerate; in such cases, imposing a false dichotomy in using the fundamental matrix or …

Learning object segmentation in image and video datasets without human supervision is a
challenging problem. Humans easily identify moving salient objects in videos using the …

Given two consecutive RGB-D images, we propose a model that estimates a dense three-
dimensional (3D) motion field, also known as scene flow. We take advantage of the fact that …