Bio
Currently, I work as an algorithm researcher in Rudich's Lab at the Weizmann Institute, specializing in computer vision and remote sensing. I earned my Ph.D. in Computer Science from Kingston University London (2021) under Professor Jean-Christophe Nebel's supervision.
Prior to that, I completed my M.Sc. in Computer Science at the Weizmann Institute of Science (2013), where I worked with Professor Ronen Basri. My academic foundation began at the Hebrew University of Jerusalem (2011), where I received my undergraduate degree in Computer Science.
During my time at Intel and Applied Materials, I gained valuable industry experience in technology development and implementation, which motivated me to pursue an MBA from The Open University of Israel (2024).
Research Interests
Computer Vision
Deep Learning
Image Processing
Machine Learning
Remote Sensing
Publications
Efficient Bayesian Detection of Faint Curved Edges in Noisy Images
Author: Nati Ofir Moderator: Ronen Basri
Weizmann Institute of Science, 2013
Fast Detection of Curved Edges at Low SNR
Nati Ofir, Meirav Galun, Boaz Nadler and Ronen Basri
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, CVPR-16 (2016)
Photometric Stereo by Hemispherical Metric Embedding
Ofer Bartal, Nati Ofir, Yaron Lipman and Ronen Basri
Springer Journal of Mathematical Imaging and Vision (JMIV), July 2017
Deep Multi-Spectral Registration using Invariant Descriptor Learning
Nati Ofir, Shai Silberstein, Hila Levi, Dani Rozenbaum, Yosi Keller and Sharon Duvdevani Bar
IEEE International Conference on Image Processing (ICIP), Athens, ICIP-18 (2018)
Registration and Fusion of Multi-Spectral Images using a Novel Edge Descriptor
Nati Ofir, Shai Silberstein, Dani Rozenbaum, Yosi Keller and Sharon Duvdevani Bar
IEEE International Conference on Image Processing (ICIP), Athens, ICIP-18 (2018)
On Detection of Faint Edges in Noisy Images
Nati Ofir, Meirav Galun, Sharon Alpert, Achi Brandt, Boaz Nadler and Ronen Basri
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), January 2019
Multi-scale Processing of Noisy Images using Edge Preservation Losses
Nati Ofir and Yosi Keller
IEEE International Conference on Pattern Recognition (ICPR), Milan, ICPR-20 (2020)
Classic versus Deep Learning Approaches to Address Computer Vision Challenges: a Study of Faint Edge Detection and Multispectral Image Registration
Author: Nati Ofir Moderator: Jean-Christophe Nebel
Kingston University London, 2021
Automatic Defect Segmentation by Unsupervised Anomaly Learning
Nati Ofir, Ran Yacobi, Omer Granoviter, Boris Levant and Ore Shtalrid
IEEE International Conference on Image Processing (ICIP), Bordeaux, ICIP-22 (2022)
Multispectral Image Fusion Based on Super Pixel Segmentation
Nati Ofir and Jean-Christophe Nebel
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Rhodes, ICASSP-23 (2023)
Defect Detection Approaches Based on Simulated Reference Image
Nati Ofir, Yotam Ben Shoshan, Ran Badanes and Boris Sherman
Israel Machine Vision Conference (IMVC), Tel-Aviv, IMVC-24 (2024)
Visible and Infrared Self-Supervised Fusion Trained on a Single Example
Nati Ofir and Jean-Christophe Nebel
arXiv (2023)
Teaching
- Software Testing (TA), The Hebrew University, Spring 2010-2011
- Information Theory (TA), Weizmann Institute, Spring 2013
- Introduction to Image Processing, The College for Academic Studies, Summer 2013
- Introduction to Computer Vision (TA), Weizmann Institute, Fall 2015
- Computer Science Instructor, Davidson Institute, 2024-Present
- Computer Science Instructor, The Open University of Israel, 2024-Present