Patents by Inventor Divyansh Agarwal
Divyansh Agarwal 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: 11989834Abstract: Devices and techniques are generally described for three dimensional room modeling. In various examples, 3D mesh data representing a room may be received. Plane data comprising a plurality of planes may be received. Each plane of the plurality of planes may represent a planar surface detected in the room. In some cases, a first plurality of wall candidates for a 3D model of the room may be determined based at least in part on the plane data. A second plurality of wall candidates for the 3D model of the room may be determined by modifying the first plurality of wall candidates based on a comparison of the first plurality of wall candidates to the 3D mesh data. The 3D model of the room may be generated based at least in part on the second plurality of wall candidates.Type: GrantFiled: June 3, 2022Date of Patent: May 21, 2024Assignee: Amazon Technologies, Inc.Inventors: Mukul Agarwal, Asfand Yar Khan, Tomas F. Yago Vicente, Divyansh Agarwal, Karl Hillesland, Kevin May, Yu Lou, Chun-Kai Wang
-
Publication number: 20240160837Abstract: Embodiments described herein provide a multi-modal search-and-summarize tool for message platforms. Specifically, the multi-modal search-and-summarize tool may monitor conversational content of different formats, e.g., text, image, video, etc., and use multi-modal summarization models to generate a summary of the conversation channel. The summarization may be conducted via a search-and-summarize process in response to a specific user query, e.g., a user may enter “what did John and Josh say about the presentation tomorrow?” The multi-modal summarization model would first search for relevant conversation messages between user John and user Josh, identify communication files of different format (e.g., text messages, emojis, multimedia attachments, etc.), and then input the communication files to respective text or image encoders to generate a summary of the communication content.Type: ApplicationFiled: November 10, 2022Publication date: May 16, 2024Inventors: Divyansh Agarwal, Chien-Sheng Wu, Tian Xie
-
Patent number: 11922575Abstract: Approaches described and suggested herein relate to generating three-dimensional representations of objects to be used to render virtual reality and augmented reality effects on personal devices such as smartphones and personal computers, for example. An initial surface mesh of an object is obtained. A plurality of silhouette masks of the object taken from a plurality of viewpoints is also obtained. A plurality of depth maps are generated from the initial surface mesh. Specifically, the plurality of depth maps are taken from the same plurality of viewpoints from which the silhouette images are taken. A volume including the object is discretized into a plurality of voxels. Each voxel is then determined to be either inside the object or outside of the object based on the silhouette masks and the depth data. A final mesh is then generated from the voxels that are determined to be inside the object.Type: GrantFiled: March 12, 2021Date of Patent: March 5, 2024Assignee: A9.com, Inc.Inventors: Himanshu Arora, Divyansh Agarwal, Arnab Dhua, Chun Kai Wang
-
Patent number: 11783560Abstract: Devices and techniques are generally described for three dimensional room modeling. In various examples, 3D mesh data representing a room may be received. Plane data comprising a plurality of planes may be received. Each plane of the plurality of planes may represent a planar surface detected in the room. In some cases, a first plurality of wall candidates for a 3D model of the room may be determined based at least in part on the plane data. A second plurality of wall candidates for the 3D model of the room may be determined by modifying the first plurality of wall candidates based on a comparison of the first plurality of wall candidates to the 3D mesh data. The 3D model of the room may be generated based at least in part on the second plurality of wall candidates.Type: GrantFiled: June 3, 2022Date of Patent: October 10, 2023Assignee: AMAZON TECHNOLOGIES, INC.Inventors: Mukul Agarwal, Asfand Yar Khan, Tomas F. Yago Vicente, Divyansh Agarwal, Karl Hillesland, Kevin May, Yu Lou, Chun-Kai Wang
-
Patent number: 11521376Abstract: System and methods are provided that generate a three-dimensional model from a physical space. While a user is scanning and/or recording the physical space with a user computing device, user speech describing the physical space is recorded. A transcript is generated from the audio captured during the scan and/or image recording of the physical space. Keywords from the transcript are used to improve computer-vision object identification, which is incorporated in the three-dimensional model.Type: GrantFiled: September 27, 2021Date of Patent: December 6, 2022Assignee: A9.com, Inc.Inventors: Arnab Dhua, Divyansh Agarwal
-
Patent number: 11138789Abstract: Approaches described and suggested herein relate to generating an enhanced point cloud representation of an objection and generating a surface mesh from the enhanced point cloud. The surface mesh can be used to render three-dimensional representations of objects on personal devices such as smartphones and personal computers, for example. Generating an enhanced point cloud of an object includes capturing a plurality of images of the object from a plurality of viewpoints about the object, generating an initial point cloud representation of the object from the plurality of images, generating a preliminary surface mesh from the point cloud using a Delauney-based meshing algorithm, and sampling points from the preliminary surface mesh. The sampled points are then added to the point cloud to form the enhanced point cloud. A final surface mesh can then be generated from the enhanced point cloud using a Poisson-based meshing algorithm.Type: GrantFiled: June 25, 2019Date of Patent: October 5, 2021Assignee: A9.COM, INC.Inventors: Himanshu Arora, Divyansh Agarwal, Arnab Dhua, Chun Kai Wang
-
Publication number: 20210201575Abstract: Approaches described and suggested herein relate to generating three-dimensional representations of objects to be used to render virtual reality and augmented reality effects on personal devices such as smartphones and personal computers, for example. An initial surface mesh of an object is obtained. A plurality of silhouette masks of the object taken from a plurality of viewpoints is also obtained. A plurality of depth maps are generated from the initial surface mesh. Specifically, the plurality of depth maps are taken from the same plurality of viewpoints from which the silhouette images are taken. A volume including the object is discretized into a plurality of voxels. Each voxel is then determined to be either inside the object or outside of the object based on the silhouette masks and the depth data. A final mesh is then generated from the voxels that are determined to be inside the object.Type: ApplicationFiled: March 12, 2021Publication date: July 1, 2021Inventors: Himanshu Arora, Divyansh Agarwal, Arnab Dhua, Chun Kai Wang
-
Patent number: 10991160Abstract: Approaches described and suggested herein relate to generating three-dimensional representations of objects to be used to render virtual reality and augmented reality effects on personal devices such as smartphones and personal computers, for example. An initial surface mesh of an object is obtained. A plurality of silhouette masks of the object taken from a plurality of viewpoints is also obtained. A plurality of depth maps are generated from the initial surface mesh. Specifically, the plurality of depth maps are taken from the same plurality of viewpoints from which the silhouette images are taken. A volume including the object is discretized into a plurality of voxels. Each voxel is then determined to be either inside the object or outside of the object based on the silhouette masks and the depth data. A final mesh is then generated from the voxels that are determined to be inside the object.Type: GrantFiled: June 25, 2019Date of Patent: April 27, 2021Assignee: A9.com, Inc.Inventors: Himanshu Arora, Divyansh Agarwal, Arnab Dhua, Chun Kai Wang
-
Publication number: 20180321233Abstract: A system, a microfluidic chip and a method are provided for counting desired cells in a body fluid that allows for a reasonable range of error in exchange for fast and cheap diagnosis. The fluid containing the cells to be measured is immobilized on a microfluidic chip and stained and the cell count is determined from optical signals that measure the amount of stain acquired by the immobilized cells.Type: ApplicationFiled: May 1, 2018Publication date: November 8, 2018Inventors: Daniel Zhang, Divyansh Agarwal, Prateek Agarwal