image 1

Matan Atzmon

I am a research scientist at NVIDIA, part of the Toronto AI Lab. Prior to that, I completed my Ph.D. studies at the Department of Computer Science and Applied Mathematics at the Weizmann Institute of Science under the supervision of Prof. Yaron Lipman.
My main research interests are developing 3D deep learning methods, learning with weak supervision, generative modeling, and equivariant network design.


Email: matzmon(at)nvidia(dot)com, Google scholar page, GitHub page Twitter

Publications

ReMatching Dynamic Reconstruction Flow

Sara Oblak, Despoina Paschalidou, Sanja Fidler, Matan Atzmon
Preprint

Abstract Arxiv Project

SpaceMesh: A Continuous Representation for Learning Manifold Surface Meshes

Tianchang Shen, Zhaoshuo Li, Marc Law, Matan Atzmon, Sanja Fidler, James Lucas, Jun Gao, Nicholas Sharp
SIGGRAPH Asia 2024

Abstract Arxiv Project

Approximately Piecewise E (3) Equivariant Point Networks

Matan Atzmon, Jiahui Huang, Francis Williams, Or Litany
International Conference on Learning Representations (ICLR) 2024

Abstract Arxiv Project Short Video Seminar Recording

Neural Kernel Surface Reconstruction

Jiahui Huang, Zan Gojcic, Matan Atzmon, Or Litany, Sanja Fidler, Francis Williams
Computer Vision and Pattern Recognition (CVPR) 2023, highlight paper

Abstract Arxiv Project Video

Ph.D. Thesis

Matan Atzmon
Weizmann Institute of Science, 2022

Paper

Frame Averaging for Equivariant Shape Space Learning

Matan Atzmon, Koki Nagano, Sanja Fidler, Sameh Khamis, Yaron Lipman
Computer Vision and Pattern Recognition (CVPR) 2022

Abstract Arxiv Project Video

Frame Averaging for Invariant and Equivariant Network Design

Omri Puny*, Matan Atzmon*, Heli Ben-Hamu*, Edward J. Smith, Ishan Misra, Aditya Grover, Yaron Lipman (*equal contribution)
International Conference on Learning Representations (ICLR) 2022, oral presentation

Abstract Arxiv Code

Augmenting Implicit Neural Shape Representations with Explicit Deformation Fields

Matan Atzmon, David Novotny, Andrea Vedaldi, Yaron Lipman
Technical report

Abstract Arxiv

SALD: Sign Agnostic Learning with Derivatives

Matan Atzmon and Yaron Lipman
International Conference on Learning Representations (ICLR) 2021

Abstract Arxiv Code Video

Isometric Autoencoders

Amos Gropp, Matan Atzmon, Yaron Lipman
Technical report

Abstract Arxiv

Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance

Lior Yariv, Yoni Kasten, Dror Moran, Meirav Galun, Matan Atzmon, Ronen Basri, Yaron Lipman
34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020), spotlight

Abstract Arxiv Code Project Page

Implicit Geometric Regularization for Learning Shapes

Amos Gropp, Lior Yariv, Niv Haim, Matan Atzmon, Yaron Lipman
International Conference on Machine Learning (ICML) 2020

Abstract Arxiv Code

SAL: Sign Agnostic Learning of Shapes from Raw Data

Matan Atzmon and Yaron Lipman
Computer Vision and Pattern Recognition (CVPR) 2020, oral presentation

Abstract Arxiv Code Video

Controlling Neural Level Sets

Matan Atzmon, Niv Haim, Lior Yariv, Ofer Israelov, Haggai Maron, Yaron Lipman
33rd Annual Conference on Neural Information Processing Systems (NeurIPS 2019)

Abstract Arxiv Code Poster
image 1

Point Convolutional Neural Networks by Extension Operators

Matan Atzmon*, Haggai Maron* and Yaron Lipman (*equal contribution)
ACM SIGGRAPH 2018

Abstract Arxiv GitHub Slides Video