1 code implementation • ECCV 2020 • Dahlia Urbach, Yizhak Ben-Shabat, Michael Lindenbaum
We introduce a new deep learning method for point cloud comparison.
no code implementations • 12 Mar 2023 • Thomas Dagès, Michael Lindenbaum, Alfred M. Bruckstein
Neural networks are omnipresent, but remain poorly understood.
1 code implementation • 11 Apr 2022 • Zeev Gutman, Ritvik Vij, Laurent Najman, Michael Lindenbaum
We found that the obtainable segmentation quality varies significantly depending on the way that the segments are specified by the hierarchy elements, and that representing a segmentation with only a few hierarchy elements is often possible.
no code implementations • 12 Oct 2020 • Mark Fonaryov, Michael Lindenbaum
In contrast to human vision, common recognition algorithms often fail on partially occluded images.
1 code implementation • 24 Apr 2020 • Dahlia Urbach, Yizhak Ben-Shabat, Michael Lindenbaum
We introduce a new deep learning method for point cloud comparison.
1 code implementation • CVPR 2020 • Or Isaacs, Oran Shayer, Michael Lindenbaum
This representation is combined with an edge map to yield a new segmentation algorithm.
no code implementations • 25 Sep 2019 • Oran Shayer, Michael Lindenbaum
Our main contribution is a new method for learning a pixel-wise representation that reflects segment relatedness.
no code implementations • 29 Jul 2019 • Thomas Dagès, Michael Lindenbaum, Alfred M. Bruckstein
Humans possess an intricate and powerful visual system in order to perceive and understand the environing world.
1 code implementation • CVPR 2019 • Yizhak Ben-Shabat, Michael Lindenbaum, Anath Fischer
In this paper, we propose a normal estimation method for unstructured 3D point clouds.
Ranked #8 on Surface Normals Estimation on PCPNet
3 code implementations • 22 Nov 2017 • Yizhak Ben-Shabat, Michael Lindenbaum, Anath Fischer
The point cloud is gaining prominence as a method for representing 3D shapes, but its irregular format poses a challenge for deep learning methods.
Ranked #57 on 3D Part Segmentation on ShapeNet-Part
no code implementations • ICCV 2017 • Elad Osherov, Michael Lindenbaum
A straightforward way to improve classification under occlusion conditions is to train the classifier using partially occluded object examples.
no code implementations • 14 Jul 2017 • Noa Arbel, Tamar Avraham, Michael Lindenbaum
In this work, we explore a different kind of contextual information: inner-scene similarity.
no code implementations • 14 Feb 2017 • Yizhak Ben-Shabat, Tamar Avraham, Michael Lindenbaum, Anath Fischer
This 3D information introduces a new conceptual change that can be utilized to improve the results of over-segmentation, which uses mainly color information, and to generate clusters of points we call super-points.
no code implementations • 24 Apr 2015 • Michael Baltaxe, Peter Meer, Michael Lindenbaum
The goal of image oversegmentation is to divide an image into several pieces, each of which should ideally be part of an object.
no code implementations • NeurIPS 2014 • Assaf Glazer, Omer Weissbrod, Michael Lindenbaum, Shaul Markovitch
The goal of hierarchical clustering is to construct a cluster tree, which can be viewed as the modal structure of a density.
no code implementations • NeurIPS 2013 • Assaf Glazer, Michael Lindenbaum, Shaul Markovitch
In this paper we introduce a novel method that can efficiently estimate a family of hierarchical dense sets in high-dimensional distributions.
no code implementations • NeurIPS 2012 • Assaf Glazer, Michael Lindenbaum, Shaul Markovitch
We propose an efficient, generalized, nonparametric, statistical Kolmogorov-Smirnov test for detecting distributional change in high-dimensional data.
no code implementations • Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 2 - Conference B: Computer Vision & Image Processing. (Cat. No.94CH3440-5) 1994 • Eldar, Yuval, Michael Lindenbaum, Moshe Porat, and Yehoshua Y. Zeevi
A new method of "farthest point strategy" (FPS) for progressive image acquisition is presented.