no code implementations • 13 Feb 2024 • Matan Atzmon, Jiahui Huang, Francis Williams, Or Litany
Integrating a notion of symmetry into point cloud neural networks is a provably effective way to improve their generalization capability.
no code implementations • CVPR 2023 • Jiahui Huang, Zan Gojcic, Matan Atzmon, Or Litany, Sanja Fidler, Francis Williams
We present a novel method for reconstructing a 3D implicit surface from a large-scale, sparse, and noisy point cloud.
no code implementations • CVPR 2022 • Matan Atzmon, Koki Nagano, Sanja Fidler, Sameh Khamis, Yaron Lipman
A natural way to incorporate symmetries in shape space learning is to ask that the mapping to the shape space (encoder) and mapping from the shape space (decoder) are equivariant to the relevant symmetries.
no code implementations • ICLR 2022 • Omri Puny, Matan Atzmon, Heli Ben-Hamu, Ishan Misra, Aditya Grover, Edward J. Smith, Yaron Lipman
For example, Euclidean motion invariant/equivariant graph or point cloud neural networks.
no code implementations • 19 Aug 2021 • Matan Atzmon, David Novotny, Andrea Vedaldi, Yaron Lipman
Implicit neural representation is a recent approach to learn shape collections as zero level-sets of neural networks, where each shape is represented by a latent code.
no code implementations • 16 Jun 2020 • Amos Gropp, Matan Atzmon, Yaron Lipman
Two sources of bad generalization are: extrinsic, where the learned manifold possesses extraneous parts that are far from the data; and intrinsic, where the encoder and decoder introduce arbitrary distortion in the low dimensional parameterization.
1 code implementation • ICLR 2021 • Matan Atzmon, Yaron Lipman
Learning 3D geometry directly from raw data, such as point clouds, triangle soups, or unoriented meshes is still a challenging task that feeds many downstream computer vision and graphics applications.
3 code implementations • NeurIPS 2020 • Lior Yariv, Yoni Kasten, Dror Moran, Meirav Galun, Matan Atzmon, Ronen Basri, Yaron Lipman
In this work we address the challenging problem of multiview 3D surface reconstruction.
4 code implementations • ICML 2020 • Amos Gropp, Lior Yariv, Niv Haim, Matan Atzmon, Yaron Lipman
Representing shapes as level sets of neural networks has been recently proved to be useful for different shape analysis and reconstruction tasks.
1 code implementation • CVPR 2020 • Matan Atzmon, Yaron Lipman
Recently, neural networks have been used as implicit representations for surface reconstruction, modelling, learning, and generation.
2 code implementations • NeurIPS 2019 • Matan Atzmon, Niv Haim, Lior Yariv, Ofer Israelov, Haggai Maron, Yaron Lipman
In turn, the sample network can be used to incorporate the level set samples into a loss function of interest.
1 code implementation • 27 Mar 2018 • Matan Atzmon, Haggai Maron, Yaron Lipman
This paper presents Point Convolutional Neural Networks (PCNN): a novel framework for applying convolutional neural networks to point clouds.
Ranked #80 on 3D Point Cloud Classification on ModelNet40