Roey Mechrez

Since September 2022 Im Head of EMEA and AI at Tulip where we transform augment the manufacturing industry with our no-code platform. Prior to that I was the CEO and Founder at BeyondMinds where I led a group of top AI researchers and engineers to build the next stage of AI operation platform. Prior to joining BeyondMinds I did my PhD at the Technion-Israel, where I worked with Prof. Lihi Zelnik-Manor. My work lies at the intersection of computer vision and deep learning. Specifically, my research interests are in realistic image generation, manipulation, and transformation, focussing on tools, algorithms, and new paradigms for photo editing and synthesis. During my PhD research I was worked on Image-to-image problems, Image Generation and GANs, Super-resolution, Photorealistic synthesis, and Template Matching. My masters and bachelors were done at Tel Aviv University in Biomedical Engineering (cum laude).



Podcast: Applied AI in Manufacturing - Startup Blueprint Podcast
Blog: See Your Manufacturing Operations in a New Light: The Power of Computer Vision
Podcast: Tourists in AI-Land
Blog: Why Did I Decide to be an Entrepreneur?
Hebrew Podcast: from a CTO to a CEO | Hebrew Article: from a CTO to a CEO
ARTICLE: The Importance of Feedback for Employees and AI
Podcast: What is Data-Centric AI? - with Roey Mechrez of BeyondMinds
Calcalist, Mind The Tech: BeyondMinds: Building an enterprise AI platform
ARTICLE: AI Adoption in Business Reaches a Turning Point. What's Next?
TechCrunch: Taking a production-centric approach to enterprisewide AI adoption
Podcast: Algorithmic challenges in bringing ML models into production
Podcast: Demystifying the Technical Challenges of AI Adoption
Podcast: Pivoting from an AI Services Firm to an AI Platform Company
TALK:The Path to an Organization-Wide Adoption of AI
ARTICLE: The long-tail of AI problems requires hyper-customized solutions, not a silver-bullet
WEBINAR:Real World AI: The path to AI value
PODCAST: Practical AI Podcast: Towards stability and robustness
ARTICLE: 5 Things Business Leaders Must Know About Adopting AI at Scale
ARTICLE: What Fraudsters and 'Black Swans' Have in Common, How AI Can Mitigate the Effects of Both
ARTICLE: How AI Can Live Up to the Hype
ARTICLE: AI Will Fuel the Financial-Services
PODCAST: 20 Minute Leaders
NVIDIA GTC21 talk: Addressing the Garbage In Garbage Out Problem in Deep Learning
iNSPIRED Ai talk: There’s a New Wave of AI Adoption Barriers to Overcome, Now
Podcast: Utilizing AI 12: Why Do Most Enterprise AI Projects Fail?
The Fintech Scaling Show Podcast: Episode 36: How to use AI at Scale with Roey Mechrez
I'm co-orginizing AIM 2020: Advances in Image Manipulation workshop and challenges on image and video manipulation at ECCV 2020.
I was orginizing Deep learning Theory and Application for Computer Vision (winter school) at the Technion.
and PIRM2018: Workshop and Challenge on Perceptual Image Restoration and Manipulation at ECCV 2018.


I'm interested in computer vision, machine learning, optimization, image processing, and computational photography. Most of my papers deal with photorealistic image generation and manipulation in the low-mid level such as perceptual super resolution and in the high semantic level such as semantic style transfer.

Self-Supervised Dynamic Networks for Covariate Shift Robustness
Tomer Cohen, Noy Shulman, Hai Morgenstern, Roey Mechrez, Erez Farha (BeyondMinds)

We propose Self-Supervised Dynamic Networks (SSDN): an input-dependent mechanism, inspired by dynamic networks, that allows a self-supervised network to predict the weights of the main network, and thus directly handle covariate shifts at test-time

Saliency Driven Image Manipulation (extended version)
Roey Mechrez, Eli Shechtman Lihi Zelnik-Manor
Machine Vision and Applications (special issue: IEEE WACV'18)
project page

The goal of this paper is to manipulating images in order to control the saliency of objects. We propose an approach that considers the internal color and saliency properties of the image.

Dynamic-Net: Tuning the Objective Without Re-training
Alon Shoshan, Roey Mechrez, Lihi Zelnik-Manor
ICCV, 2019
project page / arXiv / vision day 2018 talk

We present a first attempt at alleviating the need for re-training. Rather than fixing the network at training time, we train a ``Dynamic-Net'' that can be modified at inference time.

Adversarial Feedback Loop
Firas Shama, Roey Mechrez, Alon Shoshan, Lihi Zelnik-Manor
ICCV, 2019
project page / arXiv / vision day 2018 talk

We propose a novel method that makes an explicit use of the discriminator in test-time, in a feedback manner in order to improve the generator results.

Improving CNN Training using Disentanglement for Liver Lesion Classification in CT
Avi Ben-Cohen, Roey Mechrez, Noa Yedidia, Hayit Greenspan
To appear in EMBC 2019

We suggest the synthesis of new data by mixing the class specified and unspecified representation of different factors in the training data.

Maintain Natural Image Statistics with the Contextual Loss
Roey Mechrez*, Itamar Talmi*, Firas Shama, Lihi Zelnik-Manor
ACCV, 2018
project page / GitHub / arXiv
Results: BSD100 / PIRM / DIV2K / set5 / set14 / urban100

We use the contextual loss for two image restoration problems: super-resolution and normal estimation and reveal its relation to the KL-divergence.

The 2018 PIRM Challenge on Perceptual Image Super-resolution
Yochai Blau*, Roey Mechrez*, Radu Timofte, Tomer Michaeli, Lihi Zelnik-Manor
ECCV workshop, 2018
project page / arXiv / all workshop papers at CVF

In contrast to previous SR challenges, our evaluation methodology jointly quantifies accuracy and perceptual quality

The Contextual Loss for Image Transformation with Non-Aligned Data
Roey Mechrez*, Itamar Talmi*, Lihi Zelnik-Manor
ECCV, 2018
project page / GitHub / arXiv / video / (Oral Acceptance rate 2.4%)
Resaults: faces / animals / cool politicians / single image animation / puppet control / male2female / female2male

We suggest a new loss function for image manipulation and generation. We show some very cool applications such as semantic style transfer and single image animations.

Saliency Driven Image Manipulation
Roey Mechrez, Eli Shechtman Lihi Zelnik-Manor
WACV, 2018
project page / GitHub / arXiv / video / Best paper (people's choice)

Manipulating images in order to control the saliency of objects is the goal of this paper. We propose an approach that considers the internal color and saliency properties of the image. It changes the saliency map via an optimization framework that relies on patch-based manipulation using only patches from within the same image to maintain its appearance characteristics.

Photorealistic Style Transfer with Screened Poisson Equation
Roey Mechrez, Eli Shechtman Lihi Zelnik-Manor
BMVC, 2018
project page / GitHub / arXiv / Results

Using the Screened Poisson Equation for photorealism style transfer

Template Matching with Deformable Diversity Similarity
Itamar Talmi*, Roey Mechrez*, Lihi Zelnik-Manor
CVPR, 2017
project page / GitHub / arXiv / (Spotlight Acceptance rate 8%)

Novel measure for template matching named Deformable Diversity Similarity -- based on the diversity of feature matches between a target image window and the template

Patch-Based Segmentation with Spatial Consistency: Application to MS Lesions in Brain MRI
Roey Mechrez, Jacob Goldberger Hayit Greenspan
International Journal of Biomedical Imaging, 2016

MS Lesion Segmentation using a Multi-Channel Patch-Based Approach with Spatial Consistency
Roey Mechrez, Jacob Goldberger Hayit Greenspan
SPIE Medical Imaging. International Society for Optics and Photonics, 2015

Talks and Community service

Controlling the Latent Space at Inference Time -- Israel Vision Day 2018
Industry Talks at: Intel (Haifa), Huawei (London), Samsung (Tel-Aviv), GM (Herzelia)
Academy Talks at: HUJI and Weizmann
Photorealistic Image Synthesis and Mnipulation -- Israel Vision Day 2017
Template Matching with Deformable Diversity Similarity -- Israel Vision Day 2016
Reviewer: CVPR'18 (Outstanding Reviewer), ICCV'18, ECCV'18, PIRM'18 (area chair), CVPR'19, ICCV'19, BMVC'19, NTIRE'19 (program committee)


EE046003 Deep learning Theory and Application for Computer Vision - Spring 2019

EE046746 Applications and Algorithms in Computer Vision - Spring 2018

EE046746 Applications and Algorithms in Computer Vision - Spring 2017