17 citations · 60 across the 23 of their papers we have counts for
23 papers · 1 filter
Robust affine point matching via quadratic assignment on Grassmannians
Alexander Kolpakov, Michael Werman
Robust Affine Matching with Grassmannians (RoAM) is a new algorithm to perform affine registration of point clouds. The algorithm is based on minimizing the Frobenius distance betw…
An approach to robust ICP initialization
Alexander Kolpakov, Michael Werman
In this note, we propose an approach to initialize the Iterative Closest Point (ICP) algorithm to match unlabelled point clouds related by rigid transformations. The method is base…
DecisioNet: A Binary-Tree Structured Neural Network
Noam Gottlieb, Michael Werman
Deep neural networks (DNNs) and decision trees (DTs) are both state-of-the-art classifiers. DNNs perform well due to their representational learning capabilities, while DTs are com…
DeePaste -- Inpainting for Pasting
Levi Kassel Michael Werman
One of the challenges of supervised learning training is the need to procure an substantial amount of tagged data. A well-known method of solving this problem is to use synthetic d…
On a realization of motion and similarity group equivalence classes of labeled points in with applications to computer vision
Steven B. Damelin, David L. Ragozin, Michael Werman
We study a realization of motion and similarity group equivalence classes of labeled points in as a metric space with a computable metric. Our st…
Using a Supervised Method without supervision for foreground segmentation
Levi Kassel, Michael Werman
Neural networks are a powerful framework for foreground segmentation in video acquired by static cameras, segmenting moving objects from the background in a robust way in various c…