Tetavi Ltd.

Track160, Ltd.

Take-two Interactive Software, Inc.

Showbox Ltd.

Sportvu Ltd.

Michael Birnboim

Michael Tamir

Vsevolod Kagarlitsky

Shirley Keinan

Michael Priven

Gilad Talmon

Yair Baruch

Amir Green

Tamir Anavi

Yigal Eilam

Yaacov Chernoi

David Dreizner

Michal Heker

Alexander Yudashkin

Antonio Dello Iacono

Gal Oz

Doron Segev

David Drezner

Miky Tamir

Danielle Shor

Effi Atad

Tomer Afek

Matan Efrima

Roi Lev

Yaron Waxman

Ofer Rubinstein

Gil Wohlstadter

Sefy Kagarlitsky

Alik Mokeichev

A method for generating metadata to accompany a volumetric video for texels in an object in a volumetric video. The method comprises steps of: inputting a 2D representation of the object; identifying areas in the representation that have the same one or more properties with respect to light; and generating input material groups, where all texels in each input material group have the same properties with respect to light. There exists a correspondence between at least part of the input representation and at least part of the object in the volumetric video, so that there is a correspondence between texels in the representation and texels in the object so that output material groups can be generated from the input material groups and the properties with respect to light can be stored with the volumetric video as metadata.

Material segmentation

A computer-implemented method of generating of a database for training a neural network configured for converting 2d images into 3d models comprising steps of: (a) obtaining 3d models; (b) rendering said 3d models in a 2d format from at least one view point; and (c) collecting pairs further comprising said rendered 2d image frame and said corresponding sampled 3d models each.

Method of training a neural network configured for converting 2D images into 3D models

The present invention generally pertains to systems, methods, and non-transitory processor-readable mediums for ensuring a match between geometry and texture when playing volumetric videos in a web browser.

Volumetric video in web browser

System and method for texturing a 3D surface using 2D images sourced from a plurality of imaging devices. System and method for applying a realistic texture to a model, based on texture found in one or more two-dimensional (2D) images of the object, with the texture covering the entire 3D model even if there are portions of the object that were invisible in the 2D image. System and method which does not require machine learning, is not incapable of blending between images, and which is not incapable of filling in portions of a 3D model that are invisible in the 2D image.

Surface texturing from multiple cameras

A computer-implemented method of smoothing a transition between two mesh sequences to be rendered successively comprises steps of: (a) providing first and second mesh sequences {1} and {2} formed mesh frames, respectively, to be fused into a fused sequence; (b) selecting mesh frames gand gbeing candidates for fusing therebetween; calculating geometric rigid and/or non-rigid transformations of candidate frames gand gbelonging to said first and second mesh sequences {1} and {2}; applying calculated geometric rigid and/or non-rigid transformations to candidate frames gand gbelonging to said first and second mesh sequences {1} and {2}; calculating textural transformations of said candidate frames gand gbelonging to said first and second mesh sequences {1} and {2}; and applying calculated textural transformation to said candidate frames gand gbelonging to said first and second mesh sequences {1} and {2}.

Method of fusing mesh sequences within volumetric video

Methods and systems for generating free viewpoint videos (FVVs) based on images captured in a sports arena. A method includes projecting, onto objects within a filming area within the sports arena, a predefined pattern including a large set of features; generating, based on signals captured by each of a plurality of depth cameras, a point cloud for each depth camera, wherein the plurality of depth cameras is deployed in proximity to the filming area, wherein the captured signals are reflected off of the objects within the filming area; creating, based on the plurality of point clouds, a unified point cloud; meshing points in the unified point cloud to generate a three-dimensional (3D) model of the objects; texturing the 3D model based on images captured by the plurality of depth cameras; and rendering the textured 3D model as a FVV including a series of video frames with respect to a viewpoint.

System and method for rendering free viewpoint video for sport applications

Systems and methods for foreground/background separation and for studio production of a FVV. A method includes projecting, onto objects in a filming area within a studio, a predefined pattern including a large set of features; generating, based on signals reflected off of the objects and captured by a plurality of depth cameras deployed in proximity to the filming area, a local point cloud for each depth camera; separating, based on the local point clouds, between a background and a foreground of the filming area; creating, based on the local point clouds, a unified point cloud; meshing points in the unified point cloud to generate a 3D model of the objects; texturing the 3D model based on the separation and images captured by the depth cameras; and rendering the textured 3D model as a FVV including a series of video frames with respect to at least one viewpoint.

System and method for rendering free viewpoint video for studio applications

A method and system for improving a three-dimensional (3D) representation of objects using semantic data. The method comprises receiving an input data generated in response to captured video in a filming area; setting at least one parameter for each region in the input data; and generating a 3D representation based in part on the at least one parameter and semantic data associated with the input data.

Techniques for improving mesh accuracy using labeled inputs

A system and method for creating 3D graphics representations from video. The method includes: generating a skeletal model for each of at least one non-rigid object shown in a video feed, wherein the video feed illustrates a sports event in which at least one of the non-rigid objects is moving; determining at least one 3D rigged model for the at least one skeletal model; and rendering the at least one skeletal model as a 3D representation of the sports event, wherein rendering the 3D skeletal model further comprises wrapping each of at least one 3D skeletal model with one of the at least one 3D rigged model, each 3D skeletal model corresponding to one of the at least one skeletal model, wherein each 3D rigged model is moved according to the movement of the respective skeletal model when the 3D skeletal model is wrapped with the 3D rigged model.

Techniques for rendering three-dimensional animated graphics from video

A method and system for tracking movements of objects in a sports activity are provided. The method includes matching video captured by at least one camera with sensory data captured by each of a plurality of tags, wherein each of the at least one camera is deployed in proximity to a monitored area, wherein each of the plurality of tags is disposed on an object of a plurality of monitored objects moving within the monitored area; and determining, based on the video and sensory data, at least one performance profile for each of the monitored objects, wherein each performance profile is determined based on positions of the respective monitored object moving within the monitored area.

Techniques for object tracking

Disclosed are methods, circuits, devices, systems and associated computer executable code for composing composite content. According to embodiments, there is provided an authoring device which may facilitate acquisition or generation of one or more content segments at least partially based on one or more portions of a composite content authoring template. According to further embodiments, content segments produced by the authoring device may be automatically processed in accordance with instructions embedded within the same template used by the authoring device.

Methods, circuits, devices, systems and associated computer executable code for composing composite content

It is provided a method for converting video streams capturing a scene to video streams fitting a viewpoint configuration. The video streams are provided by video cameras, and the method includes receiving parameters associated with the viewpoint configuration, and converting video streams of the scene as captured by the video cameras to video streams fitting the viewpoint configuration. The viewpoint configuration may be a dynamic viewpoint configuration determined by a joystick module. The converting may be done using a three dimensional method, and includes separating objects of the scene from other portions of the scene. The method may includes integrating the scene into the video stream of a certain scene associated with the viewpoint configuration. Sometimes the viewpoint configuration includes a varying zoom and the converting is done using one of several methods, transition between adjacent video cameras having different zoom values, real zooming of a video camera having a motorized zoom, and digital zooming in of video streams. The converting may be done on video streams which have been captured the scene in advance before commencing the converting.

Growing community of inventors

Holon, Israel

Michael Birnboim