no code implementations • 26 Mar 2024 • Andrii Kompanets, Gautam Pai, Remco Duits, Davide Leonetti, Bert Snijder
First, we present a novel and challenging dataset comprising of images of cracks in steel bridges.
no code implementations • 23 Feb 2024 • Daan Bon, Gautam Pai, Gijs Bellaard, Olga Mula, Remco Duits
We develop a Sinkhorn like algorithm that can be efficiently implemented using fast and accurate distance approximations of the Lie group and GPU-friendly group convolutions.
no code implementations • 3 Oct 2022 • Gijs Bellaard, Daan L. J. Bon, Gautam Pai, Bart M. N. Smets, Remco Duits
Typically, G-CNNs have the advantage over CNNs that they do not waste network capacity on training symmetries that should have been hard-coded in the network.
1 code implementation • 15 Mar 2022 • Ramana Sundararaman, Gautam Pai, Maks Ovsjanikov
Establishing a correspondence between two non-rigidly deforming shapes is one of the most fundamental problems in visual computing.
1 code implementation • 19 Oct 2021 • Souhaib Attaiki, Gautam Pai, Maks Ovsjanikov
We consider the problem of computing dense correspondences between non-rigid shapes with potentially significant partiality.
no code implementations • CVPR 2021 • Gautam Pai, Jing Ren, Simone Melzi, Peter Wonka, Maks Ovsjanikov
In this paper, we provide a theoretical foundation for pointwise map recovery from functional maps and highlight its relation to a range of shape correspondence methods based on spectral alignment.
no code implementations • 30 Jul 2019 • Gautam Pai, Mor Joseph-Rivlin, Ron Kimmel
In this paper, we develop a functional map framework for the shape correspondence problem by constructing pairwise constraints using point-wise descriptors.
no code implementations • 19 Mar 2019 • Moshe Lichtenstein, Gautam Pai, Ron Kimmel
A deep learning approach to numerically approximate the solution to the Eikonal equation is introduced.
no code implementations • ICLR 2018 • Gautam Pai, Ronen Talmon, Ron Kimmel
We propose a metric-learning framework for computing distance-preserving maps that generate low-dimensional embeddings for a certain class of manifolds.
no code implementations • 16 Nov 2017 • Gautam Pai, Ronen Talmon, Alex Bronstein, Ron Kimmel
This paper explores a fully unsupervised deep learning approach for computing distance-preserving maps that generate low-dimensional embeddings for a certain class of manifolds.
no code implementations • 7 Jul 2017 • Yoni Choukroun, Gautam Pai, Ron Kimmel
Here, we incorporate the order of vertices into an operator that defines a novel spectral domain.
no code implementations • 23 Nov 2016 • Gautam Pai, Aaron Wetzler, Ron Kimmel
We propose a metric learning framework for the construction of invariant geometric functions of planar curves for the Eucledian and Similarity group of transformations.