6/3/20  - Presenting Unsupervised-k-modal-styled-content-generation in Berkeley
4/3/20  - Won the WACV Doctoral Travel Grant
2/3/20  - Presenting Unsupervised-k-modal-styled-content-generation in Stanford
​12/10/19  - CrossNet accepted to WACV
​13/8/19  - DeepAge published in Signal Processing: Image Communication
3/3/19    - Accepted CVPR 2019 Oral - IM-Net for High Resolution Video Frame Interpolation

Unsupervised K-Modal Styled Content Generation

Omry Sendik, Dani Lischinski and Daniel Cohen-Or
ACM Transactions on Graphics 2020

We introduce uMM-GAN, a novel architecture designed to better model multi-modal distributions, in an unsupervised fashion. Building upon the StyleGAN architecture, our network learns multiple modes, in a completely unsupervised manner, and combines them using a set of learned weights. We demonstrate that this approach is capable of effectively approximating a complex distribution as a superposition of multiple simple ones. We further show that uMM-GAN effectively disentangles between modes and style, thereby providing an independent degree of control over the generated content.

DeepAge: Deep Learning of face-based age estimation

Omry Sendik, Yossi Keller
Signal Processing: Image Communication 78 (2019)

We present adual Convolutional Neural Network (CNN) and SupportVector Regression (SVR) approach for face-based ageestimation. A CNN is trained for representation learning,followed by Metric Learning, after which SVR is appliedto the learned features. This allows to overcome thelack of large datasets with age annotations, by initiallytraining the CNN for face recognition.

CrossNet: Latent Cross-Consistency for Unpaired Image Translation

Omry Sendik, Dani Lischinski and Daniel Cohen-Or
The IEEE Winter Conference on Applications of Computer Vision 2019 (WACV)

We introduce a novel architecture for un-paired image translation, and explore several new regularizers enabled by it. Specifically, our architecture comprises a pair of GANs, as well as a pair of translators between their respective latent spaces. These cross-translators enable us to impose several regularizing constraints on the learnt image translation operator, collectively referred to as latent cross-consistency.

IM-Net for High Resolution Video Frame Interpolation

Tomer Peleg, Pablo Szekely, Doron Sabo and Omry Sendik
CVPR 2019

In this paper we propose IM-Net: an interpolated motion neural network. We used an economic structured architecture and end-to-end training with multi-scale tailored losses. In particular, we formulate interpolated motion estimation as classification rather than regression. IM-Net out-performs previous methods by more than 1.3dB (PSNR) ona high resolution version of the recently introduced Vimeo triplet dataset. Moreover, the network runs in less than 33msec on a single GPU for HD resolution.

What's in a Face? Metric Learning for Face Characterization

Omry Sendik, Dani Lischinski and Daniel Cohen-Or
Euro Graphics 2019

We present a method for determining which facial parts (mouth, nose, etc.) best characterize an individual, given a set of that individual’s portraits. We introduce a novel distinctiveness analysis of a set of portraits, which leverages the deep features extracted by a pre-trained face recognition CNN and a hair segmentation FCN, in the context of a weakly supervised metric learning scheme. Our analysis enables the generation of a polarized class activation map (PCAM) for an individual’s portrait via a transformation that localizes and amplifies the discriminative regions of the deep feature maps extracted by the aforementioned networks. A user study that we conducted shows that there is a surprisingly good agreement between the face parts that users indicate as characteristic and the face parts automatically selected by our method. We demonstrate a few applications of our method, including determining the most and the least representative portraits among a set of portraits of an individual, and the creation of facial hybrids: portraits that combine the characteristic recognizable facial features of two individuals. Our face characterization analysis is also effective for ranking portraits in order to find an individual’s look-alikes (Doppelgängers).

Analyzing the ability to reconstruct the moisture field using commercial microwave network data

Noam David, Omry Sendik, Hagit Messer, Huaizhu Oliver Gao, Yoav Rubin, Dorita Rostkier-Edelstein, Pinhas Alpert
Atmospheric Research

This study demonstrates for the first time the potential to reconstruct the 2-Dimensional humidity field using commercial microwave links which form the infrastructure for data transmission in cellular networks. Water vapor attenuates the waves transmitted by the system and thus these microwave links can potentially form as a virtual network for monitoring the humidity field. The results show a correlation of between 0.6 and 0.92 with root mean square differences ranging from 1.9 to 4.15 gr/m^3 between conventional humidity gauges and the humidity estimates calculated for the same points in space by the proposed technology. The results obtained are the first to point out the improved performance of humidity measurements when using data from multiple microwave links. These results indicate the tremendous potential of this novel approach for improving the initialization of meteorological forecasting models thus potentially improving the ability to cope with the dangers associated with extreme weather.

Deep Correlations for Texture synthesis

Omry Sendik and Daniel Cohen-Or
ACM Transactions on Graphics, 2017

We introduce a structural energy, based on correlations among deep features, which capture the self-similarities and regularities characterizing the texture. Specifically, we show that our technique can synthesize textures that have structures of various scales, local and nonlocal, and the combination of the two.

A New Approach to Precipitation Monitoring: A critical survey of existing technologies and challenges

Omry Sendik and Hagit Messer
IEEE Signal Processing Magazine, 2015

The goal of this article is to present a critical survey of the existing papers and works on this topic. We emphasize the works relating this topic to multidimensional signal processing. The importance of precipitation (rain, sleet, hail, snow, and any other outcomes of the condensation of water vapor that falls by virtue of gravity) is clear to any layman. Whether  it  is  required  for  the  purpose  of  precisely  measuring  past  precipitation  quantities or for generating future predictions, monitoring such phenomena has been of inter-est to humankind since early biblical days.

On the Reconstructability of Images Sampled by Random Line Projections

Omry Sendik and Hagit Messer
IEEE Conference. Israel, 2012

This  paper  addresses  the  problem  of  sampling  a  two dimensional  function  (an  image)  by  projections  along  lines  with an  arbitrary  geometry.  By  usage  of  the  Papoulis  Generalized Sampling  Expansion  theorem,  and  addressing  the  problem  of missing  samples,  we  are  able  to  state,  for  any  given  sampling realization,  which  sampling  schemes  will  yield  reconstructable images  and  what  sampling  (Nyquist)  frequency  is  required  for this   realization.   Finally,   we   apply   this   technique on   two examples,  and  demonstrate  that  with  certain  geometries  the function is reconstructable, while with others it is not.

Cellular network infrastructure- the future of fog monitoring?

Noam David, Omry Sendik, Hagit Messer and Pinhas Alpert
Bulletin of the American Meteorological Society, December 2014

In this paper, a theoretical simulation is presented in which simulated fog patches are introduced into an area where a network of links is deployed. Two-dimensional maps are generated utilizing the simulated microwave network to represent sensitivity thresholds for fog detection at three different frequencies: 20, 38, and 80 GHz. Real-data measurements of fog are also demonstrated using 38-GHz band links. The results indicate the vast future potential of commercial microwave links as an opportunistic system for monitoring fog.

On the achievable coverage of rain field mapping using measurements from a given set of microwave links

Omry Sendik and Hagit Messer
IEEE Conference, Israel, 2014

In  this  paper we  discuss the  different  problem,  of detecting  rain fields, using measurements from a given set of microwave links. By  considering  the  process  in  which  the  CWN  data  is  provided, and  by  exploiting  the  power  law  which  describes  the  relation between  the  microwave  signal  attenuation  and  the  rain  rate  per km, we develop an algorithm which generates maps depicting the minimal detectable rain rate.

A 90-nm CMOS Power Amplifier for 802.16e (WiMAX) Applications

Ofir Degani, Fabian Cossoy, Shay Shahaf, Emanuel Cohen, Vladimir Kravtsov, Omry Sendik, Debopriyo Chowdhury, Christopher D Hull and Shmuel Ravid
IEEE Transactions on Microwave Theory and Techniques, 2010

We demonstrate a single-stage 90-nm CMOS power amplifier (PA) for 2.3-2.7-GHz WiMAX (802.16e) band applications.


Image synthesis through weak supervision

On the Coverage and Reconstructability of 2D Functions Sampled by Arbitrary Line Projections with an Application to Rain Field Mapping

Speech Enhancement Employing Discrete Modulation Transforms

Analytical Mechanics


Method and system for matching stereo images

Content Aware Visual Image Pattern Matching

Detecting Periodic Patterns and Aperture Problems for Motion Eestimation

Methods for Determining Estimated Depth in an Image and Systems Thereof

Detection Device For Region Of Interest And Method Of Detecting Region Of Interest

Motion Estimation Device And Motion Estimation Method

Methods and Apparatuses for Rectifying Rolling Shutter Effects

Motion Vector Processing Device For Clustering Motion Vectors And Method Of Processing The Same

Please reload