Patents by Inventor Khushi Gupta
Khushi Gupta 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).
-
Publication number: 20240127538Abstract: This document describes scene understanding for cross reality systems using occupancy grids. In one aspect, a method includes recognizing one or more objects in a model of a physical environment generated using images of the physical environment. For each object, a bounding box is fit around the object. An occupancy grid that includes a multiple cells is generated within the bounding box around the object. A value is assigned to each cell of the occupancy grid based on whether the cell includes a portion of the object. An object representation that includes information describing the occupancy grid for the object is generated. The object representations are sent to one or more devices.Type: ApplicationFiled: February 3, 2022Publication date: April 18, 2024Inventors: Divya Ramnath, Shiyu Dong, Siddharth Choudhary, Siddharth Mahendran, Arumugam Kalai Kannan, Prateek Singhal, Khushi Gupta
-
Publication number: 20230290132Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an object recognition neural network using multiple data sources. One of the methods includes receiving training data that includes a plurality of training images from a first source and images from a second source. A set of training images are obtained from the training data. For each training image in the set of training images, contrast equalization is applied to the training image to generate a modified image. The modified image is processed using the neural network to generate an object recognition output for the modified image. A loss is determined based on errors between, for each training image in the set, the object recognition output for the modified image generated from the training image and ground-truth annotation for the training image. Parameters of the neural network are updated based on the determined loss.Type: ApplicationFiled: July 28, 2021Publication date: September 14, 2023Inventors: Siddharth MAHENDRAN, Nitin BANSAL, Nitesh SEKHAR, Manushree GANGWAR, Khushi GUPTA, Prateek SINGHAL, Tarrence VAN AS, Adithya Shricharan Srinivasa RAO
-
Patent number: 11704806Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for scalable three-dimensional (3-D) object recognition in a cross reality system. One of the methods includes maintaining object data specifying objects that have been recognized in a scene. A stream of input images of the scene is received, including a stream of color images and a stream of depth images. A color image is provided as input to an object recognition system. A recognition output that identifies a respective object mask for each object in the color image is received. A synchronization system determines a corresponding depth image for the color image. A 3-D bounding box generation system determines a respective 3-D bounding box for each object that has been recognized in the color image. Data specifying one or more 3-D bounding boxes is received as output from the 3-D bounding box generation system.Type: GrantFiled: January 12, 2022Date of Patent: July 18, 2023Assignee: Magic Leap, Inc.Inventors: Siddharth Choudhary, Divya Ramnath, Shiyu Dong, Siddharth Mahendran, Arumugam Kalai Kannan, Prateek Singhal, Khushi Gupta, Nitesh Sekhar, Manushree Gangwar
-
Publication number: 20220139057Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for scalable three-dimensional (3-D) object recognition in a cross reality system. One of the methods includes maintaining object data specifying objects that have been recognized in a scene. A stream of input images of the scene is received, including a stream of color images and a stream of depth images. A color image is provided as input to an object recognition system. A recognition output that identifies a respective object mask for each object in the color image is received. A synchronization system determines a corresponding depth image for the color image. A 3-D bounding box generation system determines a respective 3-D bounding box for each object that has been recognized in the color image. Data specifying one or more 3-D bounding boxes is received as output from the 3-D bounding box generation system.Type: ApplicationFiled: January 12, 2022Publication date: May 5, 2022Inventors: Siddharth Choudhary, Divya Ramnath, Shiyu Dong, Siddharth Mahendran, Arumugam Kalai Kannan, Prateek Singhal, Khushi Gupta, Nitesh Sekhar, Manushree Gangwar
-
Patent number: 11257300Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for scalable three-dimensional (3-D) object recognition in a cross reality system. One of the methods includes maintaining object data specifying objects that have been recognized in a scene. A stream of input images of the scene is received, including a stream of color images and a stream of depth images. A color image is provided as input to an object recognition system. A recognition output that identifies a respective object mask for each object in the color image is received. A synchronization system determines a corresponding depth image for the color image. A 3-D bounding box generation system determines a respective 3-D bounding box for each object that has been recognized in the color image. Data specifying one or more 3-D bounding boxes is received as output from the 3-D bounding box generation system.Type: GrantFiled: June 12, 2020Date of Patent: February 22, 2022Assignee: Magic Leap, Inc.Inventors: Siddharth Choudhary, Divya Ramnath, Shiyu Dong, Siddharth Mahendran, Arumugam Kalai Kannan, Prateek Singhal, Khushi Gupta, Nitesh Sekhar, Manushree Gangwar
-
Publication number: 20210407125Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for object recognition neural network for amodal center prediction. One of the methods includes receiving an image of an object captured by a camera. The image of the object is processed using an object recognition neural network that is configured to generate an object recognition output. The object recognition output includes data defining a predicted two-dimensional amodal center of the object, wherein the predicted two-dimensional amodal center of the object is a projection of a predicted three-dimensional center of the object under a camera pose of the camera that captured the image.Type: ApplicationFiled: June 24, 2021Publication date: December 30, 2021Inventors: Siddharth Mahendran, Nitin Bansal, Nitesh Sekhar, Manushree Gangwar, Khushi Gupta, Prateek Singhal
-
Publication number: 20200394848Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for scalable three-dimensional (3-D) object recognition in a cross reality system. One of the methods includes maintaining object data specifying objects that have been recognized in a scene. A stream of input images of the scene is received, including a stream of color images and a stream of depth images. A color image is provided as input to an object recognition system. A recognition output that identifies a respective object mask for each object in the color image is received. A synchronization system determines a corresponding depth image for the color image. A 3-D bounding box generation system determines a respective 3-D bounding box for each object that has been recognized in the color image. Data specifying one or more 3-D bounding boxes is received as output from the 3-D bounding box generation system.Type: ApplicationFiled: June 12, 2020Publication date: December 17, 2020Inventors: Siddharth Choudhary, Divya Ramnath, Shiyu Dong, Siddarth Mahendran, Arumugam Kalai Kannan, Prateek Singhal, Khushi Gupta, Nitesh Sekhar, Manushree Gangwar
-
Patent number: 9426170Abstract: A system and method for stemming flow of information from a negative campaign are described. A status for each node of a set of preselected nodes in a social network graph is identified. The status indicates whether a node has been infected with information from a negative campaign. A source and a flow of the negative campaign are identified based on the status of the nodes from the set of preselected nodes and a topology of the social network graph. A susceptibility score is computed for one or more nodes of the social network. The susceptibility score is computed using a measure of vulnerability of nodes that have not received the information based on the flow of the negative campaign, and a measure of reachability of nodes from the source. Nodes susceptible to adopting and spreading the information from the negative campaign are identified based on the susceptibility score.Type: GrantFiled: October 17, 2013Date of Patent: August 23, 2016Assignee: ADOBE SYSTEMS INCORPORATEDInventors: Balaji Vasan Srinivasan, Akshay Kumar, Shubham Gupta, Khushi Gupta
-
Publication number: 20150113056Abstract: A system and method for stemming flow of information from a negative campaign are described. A status for each node of a set of preselected nodes in a social network graph is identified. The status indicates whether a node has been infected with information from a negative campaign. A source and a flow of the negative campaign are identified based on the status of the nodes from the set of preselected nodes and a topology of the social network graph. A susceptibility score is computed for one or more nodes of the social network. The susceptibility score is computed using a measure of vulnerability of nodes that have not received the information based on the flow of the negative campaign, and a measure of reachability of nodes from the source. Nodes susceptible to adopting and spreading the information from the negative campaign are identified based on the susceptibility score.Type: ApplicationFiled: October 17, 2013Publication date: April 23, 2015Applicant: Adobe Systems IncorporatedInventors: Balaji Vasan Srinivasan, Akshay Kumar, Shubham Gupta, Khushi Gupta