Patents by Inventor Alex Colburn
Alex Colburn 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: 11967015Abstract: The subject technology provides a framework for learning neural scene representations directly from images, without three-dimensional (3D) supervision, by a machine-learning model. In the disclosed systems and methods, 3D structure can be imposed by ensuring that the learned representation transforms like a real 3D scene. For example, a loss function can be provided which enforces equivariance of the scene representation with respect to 3D rotations. Because naive tensor rotations may not be used to define models that are equivariant with respect to 3D rotations, a new operation called an invertible shear rotation is disclosed, which has the desired equivariance property. In some implementations, the model can be used to generate a 3D representation, such as mesh, of an object from an image of the object.Type: GrantFiled: January 8, 2021Date of Patent: April 23, 2024Assignee: Apple Inc.Inventors: Qi Shan, Joshua Susskind, Aditya Sankar, Robert Alex Colburn, Emilien Dupont, Miguel Angel Bautista Martin
-
Patent number: 11632516Abstract: Techniques are described for automated operations involving capturing and analyzing information from an interior of a house, building or other structure, for use in generating and providing a representation of that interior. Such techniques may include using a user's mobile device to capture visual data from multiple viewing locations (e.g., video captured while the mobile device is rotated for some or all of a full 360 degree rotation at each viewing location) within multiple rooms, capturing data linking the multiple viewing locations, analyzing each viewing location's visual data to create a panorama image from that viewing location, analyzing the linking data to determine relative positions/directions between at least some viewing locations, creating inter-panorama links in the panoramas to each of one or more other panoramas based on such determined positions/directions, and providing information to display multiple linked panorama images to represent the interior.Type: GrantFiled: July 5, 2021Date of Patent: April 18, 2023Assignee: MFIB Holdco, Inc.Inventors: Ivaylo Boyadzhiev, Alex Colburn, Li Guan, Qi Shan
-
Patent number: 11480433Abstract: Techniques are described for using computing devices to perform automated operations to generate mapping information using inter-connected images of a defined area, and for using the generated mapping information in further automated manners. In at least some situations, the defined area includes an interior of a multi-room building, and the generated information includes a floor map of the building, such as from an automated analysis of multiple panorama images or other images acquired at various viewing locations within the building—in at least some such situations, the generating is further performed without having detailed information about distances from the images' viewing locations to walls or other objects in the surrounding building. The generated floor map and other mapping-related information may be used in various manners, including for controlling navigation of devices (e.g., autonomous vehicles), for display on one or more client devices in corresponding graphical user interfaces, etc.Type: GrantFiled: September 17, 2021Date of Patent: October 25, 2022Assignee: Zillow, Inc.Inventors: Alex Colburn, Qi Shan, Ramin Mehran, Li Guan
-
Patent number: 11408738Abstract: Techniques are described for using computing devices to perform automated operations to generate mapping information using inter-connected images of a defined area, and for using the generated mapping information in further automated manners. In at least some situations, the defined area includes an interior of a multi-room building, and the generated information includes a floor map of the building, such as from an automated analysis of multiple panorama images or other images acquired at various viewing locations within the building—in at least some such situations, the generating is further performed without having detailed information about distances from the images' viewing locations to walls or other objects in the surrounding building. The generated floor map and other mapping-related information may be used in various manners, including for controlling navigation of devices (e.g., autonomous vehicles), for display on one or more client devices in corresponding graphical user interfaces, etc.Type: GrantFiled: September 12, 2020Date of Patent: August 9, 2022Assignee: Zillow, Inc.Inventors: Alex Colburn, Qi Shan, Ramin Mehran, Li Guan
-
Publication number: 20220003555Abstract: Techniques are described for using computing devices to perform automated operations to generate mapping information using inter-connected images of a defined area, and for using the generated mapping information in further automated manners. In at least some situations, the defined area includes an interior of a multi-room building, and the generated information includes a floor map of the building, such as from an automated analysis of multiple panorama images or other images acquired at various viewing locations within the building—in at least some such situations, the generating is further performed without having detailed information about distances from the images' viewing locations to walls or other objects in the surrounding building. The generated floor map and other mapping-related information may be used in various manners, including for controlling navigation of devices (e.g., autonomous vehicles), for display on one or more client devices in corresponding graphical user interfaces, etc.Type: ApplicationFiled: September 17, 2021Publication date: January 6, 2022Inventors: Alex Colburn, Qi Shan, Ramin Mehran, Li Guan
-
Publication number: 20210377442Abstract: Techniques are described for automated operations involving capturing and analyzing information from an interior of a house, building or other structure, for use in generating and providing a representation of that interior. Such techniques may include using a user's mobile device to capture visual data from multiple viewing locations (e.g., video captured while the mobile device is rotated for some or all of a full 360 degree rotation at each viewing location) within multiple rooms, capturing data linking the multiple viewing locations, analyzing each viewing location's visual data to create a panorama image from that viewing location, analyzing the linking data to determine relative positions/directions between at least some viewing locations, creating inter-panorama links in the panoramas to each of one or more other panoramas based on such determined positions/directions, and providing information to display multiple linked panorama images to represent the interior.Type: ApplicationFiled: July 5, 2021Publication date: December 2, 2021Inventors: Ivaylo Boyadzhiev, Alex Colburn, Li Guan, Qi Shan
-
Patent number: 11165959Abstract: Techniques are described for automated operations involving acquiring and analyzing information from an interior of a house, building or other structure, for use in generating and providing a representation of that interior. Such techniques may include using a user's mobile device to capture video data from multiple viewing locations (e.g., 360° video at each viewing location) within multiple rooms, and capturing data linking the multiple viewing locations (e.g.Type: GrantFiled: October 7, 2020Date of Patent: November 2, 2021Assignee: Zillow, Inc.Inventors: Qi Shan, Alex Colburn, Li Guan, Ivaylo Boyadzhiev
-
Publication number: 20210248811Abstract: The subject technology provides a framework for learning neural scene representations directly from images, without three-dimensional (3D) supervision, by a machine-learning model. In the disclosed systems and methods, 3D structure can be imposed by ensuring that the learned representation transforms like a real 3D scene. For example, a loss function can be provided which enforces equivariance of the scene representation with respect to 3D rotations. Because naive tensor rotations may not be used to define models that are equivariant with respect to 3D rotations, a new operation called an invertible shear rotation is disclosed, which has the desired equivariance property. In some implementations, the model can be used to generate a 3D representation, such as mesh, of an object from an image of the object.Type: ApplicationFiled: January 8, 2021Publication date: August 12, 2021Inventors: Qi SHAN, Joshua SUSSKIND, Aditya SANKAR, Robert Alex COLBURN, Emilien DUPONT, Miguel Angel BAUTISTA MARTIN
-
Patent number: 11057561Abstract: Techniques are described for automated operations involving capturing and analyzing information from an interior of a house, building or other structure, for use in generating and providing a representation of that interior. Such techniques may include using a user's mobile device to capture visual data from multiple viewing locations (e.g., video captured while the mobile device is rotated for some or all of a full 360 degree rotation at each viewing location) within multiple rooms, capturing data linking the multiple viewing locations, analyzing each viewing location's visual data to create a panorama image from that viewing location, analyzing the linking data to determine relative positions/directions between at least some viewing locations, creating inter-panorama links in the panoramas to each of one or more other panoramas based on such determined positions/directions, and providing information to display multiple linked panorama images to represent the interior.Type: GrantFiled: June 18, 2019Date of Patent: July 6, 2021Assignee: Zillow, Inc.Inventors: Ivaylo Boyadzhiev, Alex Colburn, Li Guan, Qi Shan
-
Publication number: 20210021761Abstract: Techniques are described for automated operations involving acquiring and analyzing information from an interior of a house, building or other structure, for use in generating and providing a representation of that interior. Such techniques may include using a user's mobile device to capture video data from multiple viewing locations (e.g., 360° video at each viewing location) within multiple rooms, and capturing data linking the multiple viewing locations (e.g.Type: ApplicationFiled: October 7, 2020Publication date: January 21, 2021Inventors: Qi Shan, Alex Colburn, Li Guan, Ivaylo Boyadzhiev
-
Publication number: 20200408532Abstract: Techniques are described for using computing devices to perform automated operations to generate mapping information using inter-connected images of a defined area, and for using the generated mapping information in further automated manners. In at least some situations, the defined area includes an interior of a multi-room building, and the generated information includes a floor map of the building, such as from an automated analysis of multiple panorama images or other images acquired at various viewing locations within the building—in at least some such situations, the generating is further performed without having detailed information about distances from the images' viewing locations to walls or other objects in the surrounding building. The generated floor map and other mapping-related information may be used in various manners, including for controlling navigation of devices (e.g., autonomous vehicles), for display on one or more client devices in corresponding graphical user interfaces, etc.Type: ApplicationFiled: September 12, 2020Publication date: December 31, 2020Inventors: Alex Colburn, Qi Shan, Ramin Mehran, Li Guan
-
Patent number: 10834317Abstract: Techniques are described for automated operations involving acquiring and analyzing information from an interior of a house, building or other structure, for use in generating and providing a representation of that interior. Such techniques may include using a user's mobile device to capture video data from multiple viewing locations (e.g., 360° video at each viewing location) within multiple rooms, and capturing data linking the multiple viewing locations (e.g.Type: GrantFiled: November 23, 2019Date of Patent: November 10, 2020Assignee: Zillow Group, Inc.Inventors: Qi Shan, Alex Colburn, Li Guan, Ivaylo Boyadzhiev
-
Patent number: 10809066Abstract: Techniques are described for using computing devices to perform automated operations to generate mapping information using inter-connected images of a defined area, and for using the generated mapping information in further automated manners. In at least some situations, the defined area includes an interior of a multi-room building, and the generated information includes a floor map of the building, such as from an automated analysis of multiple panorama images or other images acquired at various viewing locations within the building—in at least some such situations, the generating is further performed without having detailed information about distances from the images' viewing locations to walls or other objects in the surrounding building. The generated floor map and other mapping-related information may be used in various manners, including for controlling navigation of devices (e.g., autonomous vehicles), for display on one or more client devices in corresponding graphical user interfaces, etc.Type: GrantFiled: November 14, 2018Date of Patent: October 20, 2020Assignee: Zillow Group, Inc.Inventors: Alex Colburn, Qi Shan, Ramin Mehran, Li Guan
-
Publication number: 20200116493Abstract: Techniques are described for using computing devices to perform automated operations to generate mapping information using inter-connected images of a defined area, and for using the generated mapping information in further automated manners. In at least some situations, the defined area includes an interior of a multi-room building, and the generated information includes a floor map of the building, such as from an automated analysis of multiple panorama images or other images acquired at various viewing locations within the building—in at least some such situations, the generating is further performed without having detailed information about distances from the images' viewing locations to walls or other objects in the surrounding building. The generated floor map and other mapping-related information may be used in various manners, including for controlling navigation of devices (e.g., autonomous vehicles), for display on one or more client devices in corresponding graphical user interfaces, etc.Type: ApplicationFiled: November 14, 2018Publication date: April 16, 2020Inventors: Alex Colburn, Qi Shan, Ramin Mehran, Li Guan
-
Publication number: 20200092473Abstract: Techniques are described for automated operations involving acquiring and analyzing information from an interior of a house, building or other structure, for use in generating and providing a representation of that interior. Such techniques may include using a user's mobile device to capture video data from multiple viewing locations (e.g., 360° video at each viewing location) within multiple rooms, and capturing data linking the multiple viewing locations (e.g.Type: ApplicationFiled: November 23, 2019Publication date: March 19, 2020Inventors: Qi Shan, Alex Colburn, Li Guan, Ivaylo Boyadzhiev
-
Patent number: 10530997Abstract: Automated operations may be performed involving acquiring and analyzing information from an interior of a house, building or other structure, for use in generating and providing a representation of that interior. Such operations may include using a user's mobile device to capture video data from multiple viewing locations (e.g., 360° video at each viewing location) within multiple rooms, and capturing data linking the multiple viewing locations (e.g., by recording video, acceleration and/or other data from the mobile device as the user moves between the two viewing locations), creating a panorama image for each viewing location, analyzing the linking information to model the user's travel path and determine relative positions/directions between at least some viewing locations, creating inter-panorama links in the panoramas to each of one or more other panoramas based on such determined positions/directions, and providing information to display multiple linked panorama images to represent the interior.Type: GrantFiled: July 13, 2017Date of Patent: January 7, 2020Assignee: Zillow Group, Inc.Inventors: Qi Shan, Alex Colburn, Li Guan, Ivaylo Boyadzhiev
-
Publication number: 20190306424Abstract: Techniques are described for automated operations involving capturing and analyzing information from an interior of a house, building or other structure, for use in generating and providing a representation of that interior. Such techniques may include using a user's mobile device to capture visual data from multiple viewing locations (e.g., video captured while the mobile device is rotated for some or all of a full 360 degree rotation at each viewing location) within multiple rooms, capturing data linking the multiple viewing locations, analyzing each viewing location's visual data to create a panorama image from that viewing location, analyzing the linking data to determine relative positions/directions between at least some viewing locations, creating inter-panorama links in the panoramas to each of one or more other panoramas based on such determined positions/directions, and providing information to display multiple linked panorama images to represent the interior.Type: ApplicationFiled: June 18, 2019Publication date: October 3, 2019Inventors: Ivaylo Boyadzhiev, Alex Colburn, Li Guan, Qi Shan
-
Patent number: 10375306Abstract: Techniques are described for automated operations involving capturing and analyzing information from an interior of a house, building or other structure, for use in generating and providing a representation of that interior. Such techniques may include using a user's mobile device to capture visual data from multiple viewing locations (e.g., video captured while the mobile device is rotated for some or all of a full 360 degree rotation at each viewing location) within multiple rooms, capturing data linking the multiple viewing locations, analyzing each viewing location's visual data to create a panorama image from that viewing location, analyzing the linking data to determine relative positions/directions between at least some viewing locations, creating inter-panorama links in the panoramas to each of one or more other panoramas based on such determined positions/directions, and providing information to display multiple linked panorama images to represent the interior.Type: GrantFiled: July 13, 2017Date of Patent: August 6, 2019Assignee: Zillow Group, Inc.Inventors: Qi Shan, Alex Colburn, Li Guan, Ivaylo Boyadzhiev
-
Publication number: 20190020816Abstract: Techniques are described for automated operations involving capturing and analyzing information from an interior of a house, building or other structure, for use in generating and providing a representation of that interior. Such techniques may include using a user's mobile device to capture visual data from multiple viewing locations (e.g., video captured while the mobile device is rotated for some or all of a full 360 degree rotation at each viewing location) within multiple rooms, capturing data linking the multiple viewing locations, analyzing each viewing location's visual data to create a panorama image from that viewing location, analyzing the linking data to determine relative positions/directions between at least some viewing locations, creating inter-panorama links in the panoramas to each of one or more other panoramas based on such determined positions/directions, and providing information to display multiple linked panorama images to represent the interior.Type: ApplicationFiled: July 13, 2017Publication date: January 17, 2019Inventors: Qi Shan, Alex Colburn, Li Guan, Ivaylo Boyadzhiev
-
Publication number: 20190020817Abstract: Techniques are described for automated operations involving acquiring and analyzing information from an interior of a house, building or other structure, for use in generating and providing a representation of that interior. Such techniques may include using a user's mobile device to capture video data from multiple viewing locations (e.g., 360° video at each viewing location) within multiple rooms, and capturing data linking the multiple viewing locations (e.g.Type: ApplicationFiled: July 13, 2017Publication date: January 17, 2019Inventors: Qi Shan, Alex Colburn, Li Guan, Ivaylo Boyadzhiev