image 1

Yoni Kasten

I am a Senior Research Scientist at NVIDIA Research. I'm interested in Computer Vision and Machine Learning. My research is mostly in the domain of 3D computer vision (e.g. Camera Localization, Structure From Motion and 3D reconstruction) and has recently focused on deep neural models for computer vision problems that involve geometry. I recently completed my PhD at Weizmann Institute of Science under the supervision of Prof. Ronen Basri from the Department of Computer Science and Applied Mathematics at the Weizmann Institute of Science. I did my B.Sc. in Electrical Engineering at the Hebrew University of Jerusalem, where I also did my M.Sc. in Computer Science under the supervision of Prof. Shmuel Peleg and Prof. Michael Werman.
Email: yonikasten at gmail dot com

Teaching

  • 2021/spring (WIS): Multiple View Geometry for Computer Vision Applications (lecturer)
  • 2020/spring (WIS): Multiple View Geometry for Computer Vision Applications (lecturer)
  • 2018/winter (WIS): Introduction to Computer Vision (TA)
  • 2016/winter (HUJI): Image Processing (TA)
  • 2015/winter (HUJI): Image Processing (TA)

Publications

Neural Congealing: Aligning Images to a Joint Semantic Atlas

Dolev Ofri-Amar, Michal Geyer, Yoni Kasten, Tali Dekel
CVPR 2023

Abstract Paper Project page Code

Text2LIVE: Text-Driven Layered Image and Video Editing

Omer Bar-Tal*, Dolev Ofri-Amar*, Rafail Fridman*, Yoni Kasten, Tali Dekel
ECCV 2022

Oral presentation

Abstract Paper Project page Code

Learning to Estimate Multi-view Pose from Object Silhouettes

Yoni Kasten, True Price, David Geraghty, Jan-Michael Frahm
Recovering 6D Object Pose Workshop at ECCV 2022

Abstract Paper Presentation (by True Price)

Layered Neural Atlases for Consistent Video Editing

Yoni Kasten, Dolev Ofri, Oliver Wang, Tali Dekel
SIGGRAPH Asia 2021

Abstract Paper Project page Code

Volume Rendering of Neural Implicit Surfaces

Lior Yariv, Jiatao Gu, Yoni Kasten, Yaron Lipman
Neural Information Processing Systems 2021 (NeurIPS'21)

Oral presentation

Abstract Paper

Deep Permutation Equivariant Structure from Motion

Dror Moran*, Hodaya Koslowsky*, Yoni Kasten, Haggai Maron, Meirav Galun, Ronen Basri (*equal contribution)
International Conference on Computer Vision 2021 (ICCV'21)

Oral presentation

Abstract Paper Code
image 1

A hybrid global structure from motion method for synchronously estimating global rotations and global translations

Xin Wang, Teng Xiao, Yoni Kasten

ISPRS Journal of Photogrammetry and Remote Sensing 2021

Abstract Paper
image 1

Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance

Lior Yariv, Yoni Kasten, Dror Moran, Meirav Galun, Matan Atzmon, Ronen Basri, Yaron Lipman

Neural Information Processing Systems 2020 (NeurIPS'20)

Spotlight presentation

Abstract Paper Project Page Code
image 1

On the Similarity between the Laplace and Neural Tangent Kernels

Amnon Geifman, Abhay Yadav, Yoni Kasten, Meirav Galun, David Jacobs, Ronen Basri

Neural Information Processing Systems 2020 (NeurIPS'20)

Abstract Paper

End-To-End Convolutional Neural Network for 3D Reconstruction of Knee Bones From Bi-Planar X-Ray Images

Yoni Kasten*, Daniel Doktofsky*, Ilya Kovler* (*equal contribution)
International Workshop on Machine Learning for Medical Image Reconstruction 2020

Abstract Paper
image 1

Frequency Bias in Neural Networks for Input of Non-Uniform Density

Ronen Basri, Meirav Galun, Amnon Geifman, David Jacobs, Yoni Kasten, Shira Kritchman (alphabetical order)

International Conference on Machine Learning 2020 (ICML'20)

Abstract Paper
image 1

Averaging Essential and Fundamental Matrices in Collinear Camera Settings

Amnon Geifman*, Yoni Kasten*, Meirav Galun and Ronen Basri (*equal contribution)

Computer Vision and Pattern Recognition (CVPR'20), Seattle 2020

Abstract Paper Video Lecture (Israel Computer Vision Day 2019)
image 1

The Convergence Rate of Neural Networks for

Learned Functions of Different Frequencies

Ronen Basri, David Jacobs, Yoni Kasten and Shira Kritchman (alphabetical order)

Neural Information Processing Systems (NeurIPS'19), Vancouver 2019

Abstract Paper Code
image 1

Algebraic Characterization of Essential Matrices

and Their Averaging in Multiview Settings

Yoni Kasten*, Amnon Geifman*, Meirav Galun and Ronen Basri (*equal contribution)

International Conference on Computer Vision (ICCV'19), Seoul 2019

Abstract Paper Code Video Lecture (Israel Computer Vision Day 2019)
image 1

GPSfM: Global Projective SFM Using Algebraic Constraints

on Multi-View Fundamental Matrices

Yoni Kasten*, Amnon Geifman*, Meirav Galun and Ronen Basri (*equal contribution)

Computer Vision and Pattern Recognition (CVPR'19), Long Beach 2019

Abstract Paper Code Video Lecture (Israel Computer Vision Day 2019)
image 1

Resultant Based Incremental Recovery of Camera Pose

from Pairwise Matches

Yoni Kasten, Meirav Galun and Ronen Basri

Winter Conference on Applications of Computer Vision (WACV'19), Hilton Waikoloa Village, Hawaii 2019

Abstract Paper Code Video Lecture (Israel Computer Vision Day 2018)
image 1

Two View Constraints on the Epipoles from Few Correspondences

Yoni Kasten, Michael Werman

International Conference on Image Processing (ICIP'18), Athens 2018

Abstract Paper Buddy Search Web App (developed with Tomer Hacohen)
image 1

Fundamental Matrices from Moving Objects Using Line Motion Barcodes

Yoni Kasten, Gil Ben-Artzi, Shmuel Peleg and Michael Werman

European Conference on Computer Vision (ECCV'16), Amsterdam 2016

Abstract Paper
image 1

Camera Calibration From Dynamic Silhouettes Using Motion Barcodes

Gil Ben-Artzi,Yoni Kasten, Shmuel Peleg and Michael Werman

Computer Vision and Pattern Recognition (CVPR'16), Las Vegas 2016

Abstract Paper