Patents by Inventor Diego Prilusky
Diego Prilusky has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11463678Abstract: A system for social interaction using a photo-realistic novel view of an event includes a multi-view reconstruction system for developing transmission data of the event a plurality of client-side rendering devices, each rendering device receiving the transmission data from the multi-view reconstruction system and rendering the transmission data as the photo-realistic novel view. A method of social interaction using a photo-realistic novel view of an event includes transmitting by a server side transmission data of the event; receiving by a first user on a first rendering device the data transmission; selecting by the first user a path for rendering on the first rendering device at least on novel view; rendering by the first rendering device the at least one novel view; and saving by the user on the first rendering device novel view date for the at least one novel view.Type: GrantFiled: May 29, 2020Date of Patent: October 4, 2022Assignee: INTEL CORPORATIONInventors: Oren Haimovitch-Yogev, Matteo Shapira, Aviv Shapira, Diego Prilusky, Yaniv Ben Zvi, Adi Gilat
-
Patent number: 11451757Abstract: Methods, systems and apparatuses may provide for technology that automatically determines, based on camera calibration data and trajectory data associated with a projectile in a game, a plurality of camera angles. The technology may also automatically generate, based on the plurality of camera angles, a camera path for a volumetric content replay of a three-dimensional (3D) region of interest around a highlight moment in the game.Type: GrantFiled: September 28, 2018Date of Patent: September 20, 2022Assignee: Intel CorporationInventors: Qiang Li, Wenlong Li, Doron T Houminer, Chen Ling, Diego Prilusky
-
Publication number: 20210281810Abstract: Methods, systems and apparatuses may provide for technology that automatically determines, based on camera calibration data and trajectory data associated with a projectile in a game, a plurality of camera angles. The technology may also automatically generate, based on the plurality of camera angles, a camera path for a volumetric content replay of a three-dimensional (3D) region of interest around a highlight moment in the game.Type: ApplicationFiled: September 28, 2018Publication date: September 9, 2021Applicant: Intel CorporationInventors: Qiang Li, Wenlong Li, Doron T Houminer, Chen Ling, Diego Prilusky
-
Patent number: 10924721Abstract: Apparatus, systems, methods, and articles of manufacture are disclosed for assigning a color to a point in three-dimensional (3D) video. An example system includes an aggregator to access data from real cameras, the data including spatial coordinates and colors for a plurality of two-dimensional (2D) points in video data captured by the real cameras. The aggregator is to create a point cloud correlating the 2D points to the 3D points. The example system also includes a selector to select a subset of the real cameras based on a position of a virtual camera. In addition, the example system includes an analyzer to: select a point from the point cloud in a field of view of the virtual camera; select one of the subset of real cameras having a non-occluded view of the point and a perspective closest to that of the virtual camera; and assign a color to the point based on color data associated with the selected one of the real cameras.Type: GrantFiled: December 20, 2018Date of Patent: February 16, 2021Assignee: Intel CorporationInventors: Daniel Rivas Perpen, Diego Prilusky
-
Publication number: 20200404247Abstract: A system for social interaction using a photo-realistic novel view of an event includes a multi-view reconstruction system for developing transmission data of the event a plurality of client-side rendering devices, each rendering device receiving the transmission data from the multi-view reconstruction system and rendering the transmission data as the photo-realistic novel view. A method of social interaction using a photo-realistic novel view of an event includes transmitting by a server side transmission data of the event; receiving by a first user on a first rendering device the data transmission; selecting by the first user a path for rendering on the first rendering device at least on novel view; rendering by the first rendering device the at least one novel view; and saving by the user on the first rendering device novel view date for the at least one novel view.Type: ApplicationFiled: May 29, 2020Publication date: December 24, 2020Inventors: Oren Haimovitch-Yogev, Matteo Shapira, Aviv Shapira, Diego Prilusky, Yaniv Ben Zvi, Adi Gilat
-
Patent number: 10728528Abstract: A system for social interaction using a photo-realistic novel view of an event includes a multi-view reconstruction system for developing transmission data of the event a plurality of client-side rendering devices, each rendering device receiving the transmission data from the multi-view reconstruction system and rendering the transmission data as the photo-realistic novel view. A method of social interaction using a photo-realistic novel view of an event includes transmitting by a server side transmission data of the event; receiving by a first user on a first rendering device the data transmission; selecting by the first user a path for rendering on the first rendering device at least on novel view; rendering by the first rendering device the at least one novel view; and saving by the user on the first rendering device novel view date for the at least one novel view.Type: GrantFiled: April 1, 2015Date of Patent: July 28, 2020Assignee: Intel CorporationInventors: Oren Haimovitch-Yogev, Matteo Shapira, Aviv Shapira, Diego Prilusky, Yaniv Ben Zvi, Adi Gilat
-
Publication number: 20200145643Abstract: A method of limiting processing by a 3D reconstruction system of an environment in a 3D reconstruction of an event includes dividing by the subdivision module the volume into sub-volumes; projecting from each camera each of the sub-volumes to create a set of sub-volumes masks relative to each camera; creating an imaging mask for each camera; comparing for each camera by the subdivision module the respective imaging mask to the respective subvolume mask and extracting at least one feature from at least one imaging mask; saving by the subdivision module the at least one feature to a subspace division mask; cropping the at least one feature from the imaging frames using the subspace division mask; and processing only the at least one feature for a 3D reconstruction. The system includes cameras for recording the event in imaging frames; and a subdivision module for dividing the volume into sub-volumes.Type: ApplicationFiled: October 9, 2019Publication date: May 7, 2020Inventors: Oren Haimovitch-Yogev, Matteo Shapira, Aviv Shapira, Diego Prilusky, Yaniv Ben Zvi, Adi Gilat
-
Patent number: 10567740Abstract: A method of generating user-selectable novel views of an event on a viewing device includes reconstructing by a server system for each camera image data into at least one foreground model for the respective camera and an environment model for the respective camera; joining by the server system the foreground model for each camera to create a visual atlas of all foreground models; creating by the server system foreground mapping data for foreground image data in the visual atlas; creating by the server system environment mapping data for environment image data in each respective environment model; transmitting by the server system each compressed data in a sequence it was compressed; receiving by the viewing device all compressed data; uncompressing by the viewing device all compressed data; selecting by a user the novel view; and rendering by the viewing device each novel view.Type: GrantFiled: August 27, 2018Date of Patent: February 18, 2020Assignee: Intel CorporationInventors: Oren Haimovitch-Yogev, Matteo Shapira, Aviv Shapira, Diego Prilusky, Yaniv Ben Zvi, Adi Gilat
-
Patent number: 10491887Abstract: A method of limiting processing by a 3D reconstruction system of an environment in a 3D reconstruction of an event includes dividing by the subdivision module the volume into sub-volumes; projecting from each camera each of the sub-volumes to create a set of sub-volumes masks relative to each camera; creating an imaging mask for each camera; comparing for each camera by the subdivision module the respective imaging mask to the respective subvolume mask and extracting at least one feature from at least one imaging mask; saving by the subdivision module the at least one feature to a subspace division mask; cropping the at least one feature from the imaging frames using the subspace division mask; and processing only the at least one feature for a 3D reconstruction. The system includes cameras for recording the event in imaging frames; and a subdivision module for dividing the volume into sub-volumes.Type: GrantFiled: December 18, 2017Date of Patent: November 26, 2019Assignee: Intel CorporationInventors: Oren Haimovitch-Yogev, Matteo Shapira, Aviv Shapira, Diego Prilusky, Yaniv Ben Zvi, Adi Gilat
-
Patent number: 10477189Abstract: A system for multi-view reconstruction of a photo-realistic rendering of an event includes cameras for imaging the event with image frames; a controller having a CEM module for modeling an environment from image data of the image frames, an FES module for segmenting a foreground from the environment from image data of the image frames and constructing a 3D data representation; and a configuration engine includes a path selection module, the configuration engine for configuring and rendering the photo-realistic rendering along a path selected by a user using the path selection module, the path having at least one novel view image. The photo-realistic rendering has less than a 10% discrepancy between output pixel raster values of the novel view image and the image frames imaged by the cameras.Type: GrantFiled: April 1, 2015Date of Patent: November 12, 2019Assignee: Intel CorporationInventors: Oren Haimovitch-Yogev, Matteo Shapira, Aviv Shapira, Diego Prilusky, Yaniv Ben Zvi, Adi Gilat
-
Publication number: 20190124317Abstract: Apparatus, systems, methods, and articles of manufacture are disclosed for assigning a color to a point in three-dimensional (3D) video. An example system includes an aggregator to access data from real cameras, the data including spatial coordinates and colors for a plurality of two-dimensional (2D) points in video data captured by the real cameras. The aggregator is to create a point cloud correlating the 2D points to the 3D points. The example system also includes a selector to select a subset of the real cameras based on a position of a virtual camera. In addition, the example system includes an analyzer to: select a point from the point cloud in a field of view of the virtual camera; select one of the subset of real cameras having a non-occluded view of the point and a perspective closest to that of the virtual camera; and assign a color to the point based on color data associated with the selected one of the real cameras.Type: ApplicationFiled: December 20, 2018Publication date: April 25, 2019Inventors: Daniel Rivas Perpen, Diego Prilusky
-
Publication number: 20180367788Abstract: A method of generating user-selectable novel views of an event on a viewing device includes reconstructing by a server system for each camera image data into at least one foreground model for the respective camera and an environment model for the respective camera; joining by the server system the foreground model for each camera to create a visual atlas of all foreground models; creating by the server system foreground mapping data for foreground image data in the visual atlas; creating by the server system environment mapping data for environment image data in each respective environment model; transmitting by the server system each compressed data in a sequence it was compressed; receiving by the viewing device all compressed data; uncompressing by the viewing device all compressed data; selecting by a user the novel view; and rendering by the viewing device each novel view.Type: ApplicationFiled: August 27, 2018Publication date: December 20, 2018Inventors: Oren Haimovitch-Yogev, Matteo Shapira, Aviv Shapira, Diego Prilusky, Yaniv Ben Zvi, Adi Gilat
-
Publication number: 20180261002Abstract: A method of limiting processing by a 3D reconstruction system of an environment in a 3D reconstruction of an event includes dividing by the subdivision module the volume into sub-volumes; projecting from each camera each of the sub-volumes to create a set of sub-volumes masks relative to each camera; creating an imaging mask for each camera; comparing for each camera by the subdivision module the respective imaging mask to the respective subvolume mask and extracting at least one feature from at least one imaging mask; saving by the subdivision module the at least one feature to a subspace division mask; cropping the at least one feature from the imaging frames using the subspace division mask; and processing only the at least one feature for a 3D reconstruction. The system includes cameras for recording the event in imaging frames; and a subdivision module for dividing the volume into sub-volumes.Type: ApplicationFiled: December 18, 2017Publication date: September 13, 2018Inventors: Oren Haimovitch-Yogev, Matteo Shapira, Aviv Shapira, Diego Prilusky, Yaniv Ben Zvi, Adi Gilat
-
Patent number: 10063851Abstract: A method of generating user-selectable novel views of an event on a viewing device includes reconstructing by a server system for each camera image data into at least one foreground model for the respective camera and an environment model for the respective camera; joining by the server system the foreground model for each camera to create a visual atlas of all foreground models; creating by the server system foreground mapping data for foreground image data in the visual atlas; creating by the server system environment mapping data for environment image data in each respective environment model; transmitting by the server system each compressed data in a sequence it was compressed; receiving by the viewing device all compressed data; uncompressing by the viewing device all compressed data; selecting by a user the novel view; and rendering by the viewing device each novel view.Type: GrantFiled: April 1, 2015Date of Patent: August 28, 2018Assignee: Intel CorporationInventors: Oren Haimovitch-Yogev, Matteo Shapira, Aviv Shapira, Diego Prilusky, Yaniv Ben Zvi, Adi Gilat
-
Patent number: 9846961Abstract: A method of limiting processing by a 3D reconstruction system of an environment in a 3D reconstruction of an event includes dividing by the subdivision module the volume into sub-volumes; projecting from each camera each of the sub-volumes to create a set of sub-volumes masks relative to each camera; creating an imaging mask for each camera; comparing for each camera by the subdivision module the respective imaging mask to the respective sub-volume mask and extracting at least one feature from at least one imaging mask; saving by the subdivision module the at least one feature to a subspace division mask; cropping the at least one feature from the imaging frames using the subspace division mask; and processing only the at least one feature for a 3D reconstruction. The system includes cameras for recording the event in imaging frames; and a subdivision module for dividing the volume into sub-volumes.Type: GrantFiled: April 1, 2015Date of Patent: December 19, 2017Assignee: Intel CorporationInventors: Oren Haimovitch-Yogev, Matteo Shapira, Aviv Shapira, Diego Prilusky, Yaniv Ben Zvi, Adi Gilat
-
Publication number: 20160189421Abstract: A method of limiting processing by a 3D reconstruction system of an environment in a 3D reconstruction of an event includes dividing by the subdivision module the volume into sub-volumes; projecting from each camera each of the sub-volumes to create a set of sub-volumes masks relative to each camera; creating an imaging mask for each camera; comparing for each camera by the subdivision module the respective imaging mask to the respective sub-volume mask and extracting at least one feature from at least one imaging mask; saving by the subdivision module the at least one feature to a subspace division mask; cropping the at least one feature from the imaging frames using the subspace division mask; and processing only the at least one feature for a 3D reconstruction. The system includes cameras for recording the event in imaging frames; and a subdivision module for dividing the volume into sub-volumes.Type: ApplicationFiled: April 1, 2015Publication date: June 30, 2016Applicant: Replay Technologies Inc.Inventors: Oren Haimovitch-Yogev, Matteo Shapira, Aviv Shapira, Diego Prilusky, Yaniv Ben Zvi, Adi Gilat
-
Publication number: 20160182894Abstract: A method of generating user-selectable novel views of an event on a viewing device includes reconstructing by a server system for each camera image data into at least one foreground model for the respective camera and an environment model for the respective camera; joining by the server system the foreground model for each camera to create a visual atlas of all foreground models; creating by the server system foreground mapping data for foreground image data in the visual atlas; creating by the server system environment mapping data for environment image data in each respective environment model; transmitting by the server system each compressed data in a sequence it was compressed; receiving by the viewing device all compressed data; uncompressing by the viewing device all compressed data; selecting by a user the novel view; and rendering by the viewing device each novel view.Type: ApplicationFiled: April 1, 2015Publication date: June 23, 2016Applicant: Replay Technologies Inc.Inventors: Oren Haimovitch-Yogev, Matteo Shapira, Aviv Shapira, Diego Prilusky, Yaniv Ben Zvi, Adi Gilat
-
Publication number: 20150317822Abstract: A system for social interaction using a photo-realistic novel view of an event includes a multi-view reconstruction system for developing transmission data of the event a plurality of client-side rendering devices, each rendering device receiving the transmission data from the multi-view reconstruction system and rendering the transmission data as the photo-realistic novel view. A method of social interaction using a photo-realistic novel view of an event includes transmitting by a server side transmission data of the event; receiving by a first user on a first rendering device the data transmission; selecting by the first user a path for rendering on the first rendering device at least on novel view; rendering by the first rendering device the at least one novel view; and saving by the user on the first rendering device novel view date for the at least one novel view.Type: ApplicationFiled: April 1, 2015Publication date: November 5, 2015Applicant: Replay Technologies Inc.Inventors: Oren Haimovitch-Yogev, Matteo Shapira, Aviv Shapira, Diego Prilusky, Yaniv Ben Zvi
-
Publication number: 20150319424Abstract: A system for multi-view reconstruction of a photo-realistic rendering of an event includes cameras for imaging the event with image frames; a controller having a CEM module for modeling an environment from image data of the image frames, an FES module for segmenting a foreground from the environment from image data of the image frames and constructing a 3D data representation; and a configuration engine includes a path selection module, the configuration engine for configuring and rendering the photo-realistic rendering along a path selected by a user using the path selection module, the path having at least one novel view image. The photo-realistic rendering has less than a 10% discrepancy between output pixel raster values of the novel view image and the image frames imaged by the cameras.Type: ApplicationFiled: April 1, 2015Publication date: November 5, 2015Applicant: REPLAY TECHNOLOGIES INC.Inventors: Oren Haimovitch-Yogev, Matteo Shapira, Aviv Shapira, Diego Prilusky, Yaniv Ben Zvi