Patents by Inventor Pau Gargallo Piracés
Pau Gargallo Piracés 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: 20240087226Abstract: A geographical area, which forms an area to be represented by a model of at least a portion of a scenery, is defined. The model defines three-dimensional structures of objects depicted in a plurality of images. A plurality of new images depicting the scenery is received. The plurality of new images is acquired by a camera from one or more positions within the geographical area. It is determined whether the plurality of new images fulfill a pre-defined updating criterion. In response to a determination that the plurality of new images fulfills the updating criterion, an update of the model is initiated.Type: ApplicationFiled: October 31, 2023Publication date: March 14, 2024Inventors: Yubin Kuang, Pau Gargallo Piracés, Jan Erik Solem, Johan Gyllenspetz
-
Patent number: 11928840Abstract: A method for analysis of an image comprises: receiving (402) the image to be analyzed; processing (404) the image with a machine-learned model, wherein the machine-learned model is configured to predict at least an intrinsic parameter of the image using at least a first variable of the machine-learned model, wherein the first variable defines a relation between a radial distortion of the image and a focal length of the image; and outputting (406) the intrinsic parameter of the image. Also, methods for forming a 3D reconstruction of a scenery, for training a machine-learned model for analysis of an image and for generating a dataset of images for training a machine-learned model are disclosed.Type: GrantFiled: March 13, 2020Date of Patent: March 12, 2024Assignee: Meta Platforms, Inc.Inventors: Yubin Kuang, Pau Gargallo Piracés, Manuel Antonio López Antequera, Roger Marí Molas, Jan Erik Solem
-
Patent number: 11847742Abstract: A geographical area, which forms an area to be represented by a model of at least a portion of a scenery, is defined. A plurality of new images depicting the scenery is received. The plurality of new images is acquired by a camera from one or more positions within the geographical area. It is determined whether the plurality of new images fulfill a pre-defined updating criterion. In response to a determination that the plurality of new images fulfills the updating criterion, an update of the model is initiated. A boundary area enclosing the plurality of new images is defined. The boundary area is defined based at least in part on a distance margin between an edge of the boundary area and a new image included in the plurality of new images that is closest to the edge of the boundary area.Type: GrantFiled: February 3, 2022Date of Patent: December 19, 2023Assignee: Meta Platforms, Inc.Inventors: Yubin Kuang, Pau Gargallo Piracés, Jan Erik Solem, Johan Gyllenspetz
-
Publication number: 20220230390Abstract: A method in constructing a model of a scenery comprises: receiving (200) a plurality of images depicting the scenery, wherein each image is acquired by a camera (104) from a position at a rotational angle; creating (202) a plurality of sub-models, wherein each sub-model is created by: selecting (400) a basis image; determining (402) images related to the basis image; and determining (404) the sub-model based on the basis image and the related images, wherein the sub-model defines relative positions and rotational angles of the camera (104) for the basis image and the related images and the sub-model further defines three-dimensional structures of objects depicted in the plurality of images; and separately merging (204) the defined relative positions and rotational angles of cameras (104) for the plurality of sub-models.Type: ApplicationFiled: February 3, 2022Publication date: July 21, 2022Inventors: Yubin Kuang, Pau Gargallo Piracés, Jan Erik Solem, Johan Gyllenspetz
-
Patent number: 11282271Abstract: A method in constructing a model of a scenery comprises: receiving (200) a plurality of images depicting the scenery, wherein each image is acquired by a camera (104) from a position at a rotational angle; creating (202) a plurality of sub-models, wherein each sub-model is created by: selecting (400) a basis image; determining (402) images related to the basis image; and determining (404) the sub-model based on the basis image and the related images, wherein the sub-model defines relative positions and rotational angles of the camera (104) for the basis image and the related images and the sub-model further defines three-dimensional structures of objects depicted in the plurality of images; and separately merging (204) the defined relative positions and rotational angles of cameras (104) for the plurality of sub-models.Type: GrantFiled: April 23, 2020Date of Patent: March 22, 2022Assignee: Meta Platforms, Inc.Inventors: Yubin Kuang, Pau Gargallo Piracés, Jan Erik Solem, Johan Gyllenspetz
-
Publication number: 20210326376Abstract: Information relating to a subset of images within a set of images is received. The information includes metadata of each image. The subset of images are selected from the set of images based upon each image in the subset of images being acquired within a bounding area surrounding a geographical position of a current image. Weight information is received. The weight information controls weights to be given to a plurality of different measures of similarities. A plurality of combined measures of similarity for pairs of images in the subset of images are calculated.Type: ApplicationFiled: May 6, 2021Publication date: October 21, 2021Inventors: Jan Erik Solem, Yubin Kuang, Johan Gyllenspetz, Peter Neubauer, Pau Gargallo Piracés
-
Patent number: 11030235Abstract: The present invention relates to a method for navigating through a set of images depicting a scenery, said method comprising: receiving information relating to a subset of images within said set of images, said information comprising metadata of each image, said subset of images comprising images being acquired from a geographical position, which is within a bounding area surrounding the geographical position of a current image within the set of images; receiving weight information, said weight information controlling weights to be given to a plurality of different measures of similarities based on different types of metadata; and calculating a plurality of combined measures of similarity for pairs of images in the subset of images, said calculating being performed using said metadata and said weight information.Type: GrantFiled: December 27, 2016Date of Patent: June 8, 2021Assignee: Facebook, Inc.Inventors: Jan Erik Solem, Yubin Kuang, Johan Gyllenspetz, Peter Neubauer, Pau Gargallo Piracés
-
Publication number: 20200258297Abstract: A method in constructing a model of a scenery comprises: receiving (200) a plurality of images depicting the scenery, wherein each image is acquired by a camera (104) from a position at a rotational angle; creating (202) a plurality of sub-models, wherein each sub-model is created by: selecting (400) a basis image; determining (402) images related to the basis image; and determining (404) the sub-model based on the basis image and the related images, wherein the sub-model defines relative positions and rotational angles of the camera (104) for the basis image and the related images and the sub-model further defines three-dimensional structures of objects depicted in the plurality of images; and separately merging (204) the defined relative positions and rotational angles of cameras (104) for the plurality of sub-models.Type: ApplicationFiled: April 23, 2020Publication date: August 13, 2020Applicant: Mapillary ABInventors: Yubin Kuang, Pau Gargallo Piracés, Jan Erik Solem, Johan Gyllenspetz
-
Patent number: 10672186Abstract: A method in constructing a model of a scenery comprises: receiving (200) a plurality of images depicting the scenery, wherein each image is acquired by a camera (104) from a position at a rotational angle; creating (202) a plurality of sub-models, wherein each sub-model is created by: selecting (400) a basis image; determining (402) images related to the basis image; and determining (404) the sub-model based on the basis image and the related images, wherein the sub-model defines relative positions and rotational angles of the camera (104) for the basis image and the related images and the sub-model further defines three-dimensional structures of objects depicted in the plurality of images; and separately merging (204) the defined relative positions and rotational angles of cameras (104) for the plurality of sub-models.Type: GrantFiled: June 28, 2016Date of Patent: June 2, 2020Assignee: MAPILLARY ABInventors: Yubin Kuang, Pau Gargallo Piracés, Jan Erik Solem, Johan Gyllenspetz
-
Publication number: 20180365891Abstract: A method in constructing a model of a scenery comprises: receiving (200) a plurality of images depicting the scenery, wherein each image is acquired by a camera (104) from a position at a rotational angle; creating (202) a plurality of sub-models, wherein each sub-model is created by: selecting (400) a basis image; determining (402) images related to the basis image; and determining (404) the sub-model based on the basis image and the related images, wherein the sub-model defines relative positions and rotational angles of the camera (104) for the basis image and the related images and the sub-model further defines three-dimensional structures of objects depicted in the plurality of images; and separately merging (204) the defined relative positions and rotational angles of cameras (104) for the plurality of sub-models.Type: ApplicationFiled: June 28, 2016Publication date: December 20, 2018Applicant: Mapillary ABInventors: Yubin Kuang, Pau Gargallo Piracés, Jan Erik Solem, Johan Gyllenspetz