Elias Nehme

I am a PhD Candidate at the Electrical Engineering department of the Technion, jointly supervised by Prof. Tomer Michaeli and Prof. Yoav Shechtman. Prior to that, I did my bachelors in Biomedical Engineering also at the Technion.

My research interests lie at the intersection of computational imaging and machine learning, where I mostly work on next generation cameras employing co-designed Computational Optics to recover physical properties of the imaged scene. Specifically, my latest works were on end-to-end learning of optics and image processing for precise depth estimation under challenging scenarios in the revolutionary field of super-resolution microscopy (Noble Prize in Chemistry in 2014). I also frequently collaborate with Daniel Freedman from Google Research center in Haifa.

Email  /  CV  /  Google Scholar  /  Linkedin  /  Github  /  Twitter

Sep 21, 2023 - NPPC was accepted to NeurIPS 2023.

Jun 01, 2023 - I gave an invited talk on Intelligent Microscopy at the AI for Scientific Data Analysis Mini-conference.

Dec 21, 2022 - The optimal Multicolor 3D PSF work now appears in Intelligent Computing.

May 20, 2022 - Our cell-cycle dependent chromatin dynamics work now appears in iScience.

Feb 09, 2022 - Our ICCP 2021 work won an Excellent Paper Award at the MLIS-TCE Conference.

Oct 04, 2021 - I started a Research Scientist Intern position at Verily (=Google Life Sciences).

Jul 19, 2021 - Deep-ROCS now appears in Optics Express.

May 27, 2021 - QAFKA now appears in The Journal of Physical Chemistry B.

May 24, 2021 - The Liquid-immersed Optics paper now appears in Nature Communications.

Apr 15, 2021 - The collaborative project ZeroCostDL4Mic now appears in Nature Communications.

Feb 28, 2021 - Our Multi-PSF Learning work was accepted to ICCP 2021 and selected for a special issue of TPAMI.

Feb 17, 2021 - I received the Jacobs-Qualcomm Fellowship for Outstanding Ph.D. Students 2020-2021.

Oct 19, 2020 - DeepSTORM3D was covered in a Nature Methods Technology Feature on smart microscopy.

Aug 23, 2020 - I received the VATAT Prize for Research in Applied Data Science 2019.

Jun 16, 2020 - DeepSTORM3D was covered in YNET, Jerusalem Post, American Technion Society, and Glocalist!

Jun 14, 2020 - DeepSTORM3D was featured on the cover of the Lorry I. Lokey Interdisciplinary center Annual Report.

Jan 25, 2020 - DeepSTORM is the Top-cited article in Optica from 2018 with over 200 citations!

Jan 09, 2019 - DeepSTORM3D won the Best Poster Award at QBI 2019.

Jun 20, 2018 - DeepSTORM won the Lev-Margulis Prize at ISM 2018.

May 31, 2018 - DeepSTORM was covered in a Nature Methods Research Highlight.

It is possible to learn the input-adaptive top posterior PCs and visualize reconstruction uncertainty in imaging inverse problems.

Multicolor 3D PSF engineering enables measuring distance between 2 fluorescently tagged DNA loci in yeast cells.

Cell-cycle-dependent chromatin dynamics in live cells can be quantified with high spatiotemporal resolution using end-to-end learned optics and image processing.

Efficient numerical combination of a set of differently illuminated images retrieves high-frequency information from a small number of speckle images.

Extracting and analyzing blinking events of fluorophore clusters with neural networks enables quantification of oligomerization level in membrane receptors.

Diffractive Optical Elements fabrication can be made orders of magntiude cheaper by immersing 3D printed designs in a near-index-matched solution.

Given a budget of signal photons, we learn the optimal wavefront codes for recovering the depth of nanometric point sources under challenging conditions.

Self-explanatory collection of Colab notebooks to simplify access and use of deep learning in microscopy.

Leveraging PSF engineering it is possible to profile the topology of dynamic microsurface in 3D without scanning.

We address the challenge of dense 3D localization from a single 2D image by harnessing neural networks for both acquisition design and image processing.

Vectorial phase retreival facilitated by utilizing Wirtinger flow and vectorial optics.

Temporal convolutional networks can be employed to classify many short single-particle trajectories by diffusion type.

Using a physical simulator we learn a neural network that achieves SotA performance in dense 2D localization microscopy.

The course focuses on deep generative models for images describing practical strategies for learning high-dimensional probability distributions from samples.

The course focuses on fundamental problems in computer vision describing practical solutions including state-of-the-art deep learning approaches.

The course surveys recent computational imaging techniques co-designing optical sensors and data processing algorithms to advance imaging capabilities.

The course focuses on fundamental approaches in biological signal processing including linear filtering, correlation functions, non-stationary signals, and point processes.

Fundamentals of biosignal and bioimage processing delivered to electronics high school teachers.

Website credits to Jon Barron.