Tommer Leyvand

Tommer Leyvand


Ambitious and experienced software engineering leader with a track record of driving innovation and execution of product and platform teams with a main applied-research component.

I joined Facebook in Jan 2016 and currently lead the AI Camera group, tasked with developing and perfecting advanced real-time computational photography and image understanding techniques that let us enhance images and videos, track and augment faces, bodies, and the 3D world, and capture and share the 3D world with high fidelity.We balance both research and product, building a use-case focused research portfolio while delivering state-of-the-art capabilities and new experiences supporting our Mobile AR Platform and other product teams across Facebook.

Prior to Facebook, I worked at Microsoft for ten years building advanced AI/ML platforms targeting integrated HW/SW consumer devices, as the director for HoloLens and Kinect software engineering teams. I hold a graduate degree from Tel-Aviv University, Israel

On Google ScholarOn LinkedInOn Facebook

Recent work from my amazing team at Facebook (see more here)

Old Personal Publications

Exemplar-Based Human Action Pose Correction and Tagging Combining Body Pose, Gaze, and Gesture to Determine Intention to Interact in Vision-Based  Interfaces Exemplar-Based Human Pose Correction Paper  YouTube Video
Julia Schwarz, Charles Marais, Tommer Leyvand, Scott E. Hudson, Jennifer Mankoff
CHI 2014
Combining Body Pose, Gaze, and Gesture to Determine Intention
Vision-based interfaces, such as those made popular by the Microsoft Kinect, suffer from the Midas Touch problem: every user motion can be interpreted as an interaction. In response, we developed an algorithm that combines facial features, body pose and motion to approximate a user’s intention to interact with the system. We show how this can be used to determine when to pay attention to a user’s actions and when to ignore them. To demonstrate the value of our approach, we present results from a 30-person lab study conducted to compare four engagement algorithms in single and multi-user scenarios. We found that combining intention to interact with a “raise an open hand in front f you” gesture yielded the best results. The latter approach offers a 12% improvement in accuracy and a 20% reduction in time to engage over a baseline “wave to engage” gesture currently used on the Xbox 360. More ...

Exemplar-Based Human Action Pose Correction and Tagging Exemplar-Based Human Action Pose Correction and Tagging Exemplar-Based Human Pose Correction Paper 
Wei Shen, Ke Deng, Xiang Bai, Tommer Leyvand, Baining Guo, and Zhuowen Tu
CVPR 2012
Exemplar-Based Human Action Pose Correction and Tagging
The launch of Xbox Kinect has built a very successful computer vision product and made a big impact to the gaming industry; this sheds lights onto a wide variety of potential applications related to action recognition. The accurate estimation of human poses from the depth image is universally a critical step. However, existing pose estimation systems exhibit failures when faced severe occlusion. In this paper, we propose an exemplar-based method to learn to correct the initially estimated poses. We learn an inhomogeneous systematic bias by leveraging the exemplar information within specific human action domain. Our algorithm is illustrated on both joint-based skeleton correction and tag prediction. In the  experiments, significant improvement is observed over the contemporary approaches, including what is delivered by the current Kinect system.

Kinect ID Kinect Identity: Technology and Experience Beautification PaperMSR Video
Tommer Leyvand, Casey Meekhof, Yi-Chen Wei, Jian Sun, and Baining Guo
IEEE Computer, vol. 44, no. 4, pp. 94-96. 2011.
Kinect Identity: Technology and Experience
This IEEE Computer article is a high-level introduction to how Kinect performs player identity recognition on the Xbox 360, what we call 'Kinect Identity'.

Additional details and references to related facial-recognition publications are available here. MSR video is available here.

Data-Driven Enhancement of Facial Attractiveness Beautification Paper YouTube Video
Tommer Leyvand, Daniel Cohen-Or, Gideon Dror and Dani Lischinski
In this work we focus on the challenging problem of enhancing the aesthetic appeal (or the attractiveness) of human faces in frontal photographs (portraits), while maintaining close similarity with the original. The key component in our approach is an automatic facial attractiveness
engine trained on datasets of faces with accompanying facial attractiveness ratings collected from groups of human raters. More ...

Digital Face Beautification SIGGRAPH 2006, Technical Sketch page (here)

A Machine Learning Predictor of Facial Attractiveness Revealing Human-Like Psychophysical Biases Attractiveness Paper
Amit Kagian, , Gideon Dror, Tommer Leyvand, Isaac Meilijson, Daniel Cohen-Or, Eytan Ruppin
Vision Research 48 (2008) 235–243
Recent psychological studies have strongly suggested that humans share common visual preferences for facial attractiveness. Here, we present a learning model that automatically extracts measurements of facial features from raw images and obtains human-level performance in predicting facial attractiveness ratings. The machine’s ratings are highly correlated with mean human ratings, markedly improving on recent machine learning studies of this task. Simulated psychophysical experiments with virtually manipulated images reveal preferences in the machine’s judgments that are remarkably similar to those of humans. Thus, a model trained explicitly to capture a specific operational performance criteria, implicitly captures basic human psychophysical characteristics.

Color Harmonization (before and after) Color Harmonization Color Harmonization Paper Color Harmonization SIGGRAPH 2006 Presentation
Daniel Cohen-Or, Olga Sorkine, Ran Gal, Tommer Leyvand and Ying-Qing Xu
Color Harmonization Paper 
Harmonic colors are sets of colors that are aesthetically pleasing in terms of human visual perception. In this paper, we present a method that enhances the harmony among the colors of a given photograph or of a general image, while remaining faithful, as much as possible, to the original colors. Given a color image, our method finds the best harmonic scheme for the image colors. It then allows a graceful shifting of hue values so as to fit the harmonic scheme while considering spatial coherence among colors of neighboring pixels using an optimization technique. The results demonstrate that our method is capable of automatically enhancing the color "look-and-feel" of an ordinary image.

Interactive Object Segmentation in Video by Fitting Splines to Graph Cuts Poster
Iddo Drori, Tommer Leyvand, Daniel Cohen-Or and Hezy Yeshurun
ACM SIGGRAPH 2004 Posters Session
Segmentation Poster
Object segmentation in image sequences is one of the fundamental problems in computer vision and graphics. This problem is usually addressed either by discrete representations which are currently manifested by graph partitioning techniques, or by continuous methods typically referred to as active contours. In this work we take a unified approach by fitting splines to graph cuts. The strengths of this approach stem from the dual discrete and continuous representations and from allowing the user to refine the result of the cut by fitting a new spline to it and modifying its points. More ...

Video Operations in the Gradient Domain Technical Report
Iddo Drori, Tommer Leyvand, Shachar Fleishman, Daniel Cohen-Or and Hezy Yeshurun
Technical Report, May 2004
Fusion of image sequences is a fundamental operation in numerous video applications and usually
consists of segmentation, matting and compositing. We present a unified framework for performing
these operations on video in the gradient domain. Our approach consists of 3D graph cut computation followed by reconstruction of a new 3D vector field by solving the Poisson equation. We demonstrate the applicability of smooth video transitions by fusing pairs for video mosaics, video folding, and video texture synthesis, and demonstrate the applicability of sharp video transitions by video segmentation, video trimap extraction and 3D compositing into a new sequence. Our results demonstrate that our method maintains coherence of the video matte and composite, and avoids temporal artifacts. More ...

Ray Space Factorization for From-Region Visibility Visibility Paper YouTube Video Color Harmonization SIGGRAPH 2006 Presentation
Tommer Leyvand, Olga Sorkine and Daniel Cohen-Or
Ray Space Factorization
This paper present a conservative occlusion culling method based on factorizing the 4D from-region visibility problem into horizontal and vertical components. The visibility of the two components is solved asymmetrically: the horizontal component is based on a parameterization of the ray space, and the visibility of the vertical component is solved by incrementally merging umbrae. The technique is designed so that the horizontal and vertical operations can be efficiently realized together by modern graphics hardware. More ...



Example of smooth image completion Advanced Topic in Computer Graphics / Spring 2004: Exercise 1 - Poisson Image Editing

This exercise is an introduction to gradient domain image editing. We start with the simpler smooth image completion operation (an example input/out pair is on the left). We continue to describe the poisson image cloning technique that involves cloning pixel-gradients instead of pixel values and usually results in a smoother blending. The exercise material includes the presentation slides and full solution source-code. More ...


CityGenCityGen - Procedural Urban Model Generator

CityGen is a procedural 3D model generator application aimed for generating random urban models. These models are generated from an XML construction file using several simple operations and random inputs. Developed as a side project from my "Ray-Space Factorization for From-Region Visibility" paper. More ...


 07/07/2005, V0.9 of CityGen released (download here)


Online source-code:

© 2003-2018 Tommer Leyvand

Last updated July 2018