Patents by Inventor Georgios Papandreou

Georgios Papandreou 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: 11908083
    Abstract: Methods and systems are disclosed for performing operations comprising: receiving a video that includes a depiction of a real-world object; generating a three-dimensional (3D) body mesh associated with the real-world object that tracks movement of the real-world object across frames of the video; obtaining an external mesh associated with an augmented reality element; automatically establishing a correspondence between the 3D body mesh associated with the real-world object and the external mesh; deforming the external mesh based on movement of the real-world object and the established correspondence with the 3D body mesh; and modifying the video to include a display of the augmented reality element based on the deformed external mesh.
    Type: Grant
    Filed: August 31, 2021
    Date of Patent: February 20, 2024
    Assignee: Snap Inc.
    Inventors: Yanli Zhao, Matan Zohar, Brian Fulkerson, Georgios Papandreou, Haoyang Wang
  • Publication number: 20230316665
    Abstract: Methods and systems are disclosed for performing operations for applying augmented reality elements to a person depicted in an image. The operations include receiving an image that includes data representing a depiction of a person; generating a segmentation of the data representing the person depicted in the image; extracting a portion of the image corresponding to the segmentation of the data representing the person depicted in the image; applying a machine learning model to the portion of the image to predict a surface normal tensor for the data representing the depiction of the person, the surface normal tensor representing surface normals of each pixel within the portion of the image; and applying one or more augmented reality (AR) elements to the image based on the surface normal tensor.
    Type: Application
    Filed: June 16, 2022
    Publication date: October 5, 2023
    Inventors: Madiyar Aitbayev, Brian Fulkerson, Riza Alp Guler, Georgios Papandreou, Himmy Tam
  • Publication number: 20230316666
    Abstract: Methods and systems are disclosed for performing operations for applying augmented reality elements to a person depicted in an image. The operations include receiving an image that includes data representing a depiction of a person; extracting a portion of the image; applying a first machine learning model stage to the portion to predict a depth of a point of interest for the data representing the depiction of the person; applying a second machine learning model stage to the portion of the image to predict a relative depth of each pixel in the portion of the image to the predicted depth of the point of interest; generating dense depth reconstruction of the data representing the depiction of the person based on outputs of the first and second stages of the machine learning model; and applying one or more AR elements to the image based on the dense depth reconstruction.
    Type: Application
    Filed: June 16, 2022
    Publication date: October 5, 2023
    Inventors: Madiyar Aitbayev, Brian Fulkerson, Riza Alp Guler, Georgios Papandreou, Himmy Tam
  • Publication number: 20230267687
    Abstract: Systems and methods for reconstructing 3D models of human bodies from 2D images that counts for perspective and/or distortion effects are provided. The systems and methods include reconstructing a three-dimensional model of an object in a three-dimensional scene from a two-dimensional image comprising an image of the object. The systems and methods include determining an absolute depth of a key point of the object in the image; determining, using the absolute depth of the key point, a three-dimensional position of the key point in the three-dimensional scene; generating, using a neural network, a three-dimensional representation of the object, the three-dimensional representation comprising mesh nodes defined in a coordinate system relative to the key point; and positioning the three-dimensional representation of the object in the scene based on the position of the key point by applying a position dependent rotation to the three-dimensional object.
    Type: Application
    Filed: May 2, 2023
    Publication date: August 24, 2023
    Inventors: Georgios Papandreou, Iason Kokkinos
  • Patent number: 11688136
    Abstract: Systems and methods for reconstructing 3D models of human bodies from 2D images that counts for perspective and/or distortion effects are provided. The systems and methods include reconstructing a three-dimensional model of an object in a three-dimensional scene from a two-dimensional image comprising an image of the object. The systems and methods include determining an absolute depth of a key point of the object in the image; determining, using the absolute depth of the key point, a three-dimensional position of the key point in the three-dimensional scene; generating, using a neural network, a three-dimensional representation of the object, the three-dimensional representation comprising mesh nodes defined in a coordinate system relative to the key point; and positioning the three-dimensional representation of the object in the scene based on the position of the key point by applying a position dependent rotation to the three-dimensional object.
    Type: Grant
    Filed: March 2, 2021
    Date of Patent: June 27, 2023
    Assignee: SNAP INC.
    Inventors: Georgios Papandreou, Iason Kokkinos
  • Publication number: 20230061875
    Abstract: Methods and systems are disclosed for performing operations comprising: receiving a video that includes a depiction of a real-world object; generating a three-dimensional (3D) body mesh associated with the real-world object that tracks movement of the real-world object across frames of the video; obtaining an external mesh associated with an augmented reality element; automatically establishing a correspondence between the 3D body mesh associated with the real-world object and the external mesh; deforming the external mesh based on movement of the real-world object and the established correspondence with the 3D body mesh; and modifying the video to include a display of the augmented reality element based on the deformed external mesh.
    Type: Application
    Filed: August 31, 2021
    Publication date: March 2, 2023
    Inventors: Yanli Zhao, Matan Zohar, Brian Fulkerson, Georgios Papandreou, Haoyang Wang
  • Publication number: 20220375247
    Abstract: Aspects of the present disclosure involve a system and a method for performing operations comprising: receiving a two-dimensional continuous surface representation of a three-dimensional object, the continuous surface comprising a plurality of landmark locations; determining a first set of soft membership functions based on a relative location of points in the two-dimensional continuous surface representation and the landmark locations; receiving a two-dimensional input image, the input image comprising an image of the object; extracting a plurality of features from the input image using a feature recognition model; generating an encoded.
    Type: Application
    Filed: July 15, 2022
    Publication date: November 24, 2022
    Inventors: Iason Kokkinos, Georgios Papandreou, Riza Alp Guler
  • Publication number: 20220358770
    Abstract: This specification relates to reconstructing three-dimensional (3D) scenes from two-dimensional (2D) images using a neural network. According to a first aspect of this specification, there is described a method for creating a three-dimensional reconstruction of a scene with multiple objects from a single two-dimensional image, the method comprising: receiving a single two-dimensional image; identifying all objects in the image to be reconstructed and identifying the type of said objects; estimating a three-dimensional representation of each identified object; estimating a three-dimensional plane physically supporting all three-dimensional objects; and positioning all three-dimensional objects in space relative to the supporting plane.
    Type: Application
    Filed: June 17, 2020
    Publication date: November 10, 2022
    Inventors: Riza Alp Guler, Georgios Papandreou, Iason Kokkinos
  • Patent number: 11430247
    Abstract: Aspects of the present disclosure involve a system and a method for performing operations comprising: receiving a two-dimensional continuous surface representation of a three-dimensional object, the continuous surface comprising a plurality of landmark locations; determining a first set of soft membership functions based on a relative location of points in the two-dimensional continuous surface representation and the landmark locations; receiving a two-dimensional input image, the input image comprising an image of the object; extracting a plurality of features from the input image using a feature recognition model; generating an encoded feature representation of the extracted features using the first set of soft membership functions; generating a dense feature representation of the extracted features from the encoded representation using a second set of soft membership functions; and processing the second set of soft membership functions and dense feature representation using a neural image decoder model to
    Type: Grant
    Filed: November 13, 2020
    Date of Patent: August 30, 2022
    Assignee: Snap Inc.
    Inventors: Iason Kokkinos, Georgios Papandreou, Riza Alp Guler
  • Publication number: 20210398351
    Abstract: Systems and methods for reconstructing 3D models of human bodies from 2D images that counts for perspective and/or distortion effects are provided. The systems and methods include reconstructing a three-dimensional model of an object in a three-dimensional scene from a two-dimensional image comprising an image of the object. The systems and methods include determining an absolute depth of a key point of the object in the image; determining, using the absolute depth of the key point, a three-dimensional position of the key point in the three-dimensional scene; generating, using a neural network, a three-dimensional representation of the object, the three-dimensional representation comprising mesh nodes defined in a coordinate system relative to the key point; and positioning the three-dimensional representation of the object in the scene based on the position of the key point by applying a position dependent rotation to the three-dimensional object.
    Type: Application
    Filed: March 2, 2021
    Publication date: December 23, 2021
    Inventors: Georgios Papandreou, Iason Kokkinos
  • Patent number: 11074504
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for instance segmentation. In one aspect, a system generates: (i) data identifying one or more regions of the image, wherein an object is depicted in each region, (ii) for each region, a predicted type of object that is depicted in the region, and (iii) feature channels comprising a plurality of semantic channels and one or more direction channels. The system generates a region descriptor for each of the one or more regions, and provides the region descriptor for each of the one or more regions to a segmentation neural network that processes a region descriptor for a region to generate a predicted segmentation of the predicted type of object depicted in the region.
    Type: Grant
    Filed: November 14, 2018
    Date of Patent: July 27, 2021
    Assignee: Google LLC
    Inventors: Liang-Chieh Chen, Alexander Hermans, Georgios Papandreou, Gerhard Florian Schroff, Peng Wang, Hartwig Adam
  • Publication number: 20210150197
    Abstract: Aspects of the present disclosure involve a system and a method for performing operations comprising: receiving a two-dimensional continuous surface representation of a three-dimensional object, the continuous surface comprising a plurality of landmark locations; determining a first set of soft membership functions based on a relative location of points in the two-dimensional continuous surface representation and the landmark locations; receiving a two-dimensional input image, the input image comprising an image of the object; extracting a plurality of features from the input image using a feature recognition model; generating an encoded feature representation of the extracted features using the first set of soft membership functions; generating a dense feature representation of the extracted features from the encoded representation using a second set of soft membership functions; and processing the second set of soft membership functions and dense feature representation using a neural image decoder model to
    Type: Application
    Filed: November 13, 2020
    Publication date: May 20, 2021
    Inventors: Iason Kokkinos, Georgios Papandreou, Riza Alp Guler
  • Publication number: 20210081796
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes obtaining training data for a dense image prediction task; and determining an architecture for a neural network configured to perform the dense image prediction task, comprising: searching a space of candidate architectures to identify one or more best performing architectures using the training data, wherein each candidate architecture in the space of candidate architectures comprises (i) the same first neural network backbone that is configured to receive an input image and to process the input image to generate a plurality of feature maps and (ii) a different dense prediction cell configured to process the plurality of feature maps and to generate an output for the dense image prediction task; and determining the architecture for the neural network based on the best performing candidate architectures.
    Type: Application
    Filed: November 30, 2020
    Publication date: March 18, 2021
    Inventors: Barret Zoph, Jonathon Shlens, Yukun Zhu, Maxwell Donald Collins, Liang-Chieh Chen, Gerhard Florian Schroff, Hartwig Adam, Georgios Papandreou
  • Patent number: 10853726
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes obtaining training data for a dense image prediction task; and determining an architecture for a neural network configured to perform the dense image prediction task, comprising: searching a space of candidate architectures to identify one or more best performing architectures using the training data, wherein each candidate architecture in the space of candidate architectures comprises (i) the same first neural network backbone that is configured to receive an input image and to process the input image to generate a plurality of feature maps and (ii) a different dense prediction cell configured to process the plurality of feature maps and to generate an output for the dense image prediction task; and determining the architecture for the neural network based on the best performing candidate architectures.
    Type: Grant
    Filed: May 29, 2019
    Date of Patent: December 1, 2020
    Assignee: Google LLC
    Inventors: Barret Zoph, Jonathon Shlens, Yukun Zhu, Maxwell Donald Emmet Collins, Liang-Chieh Chen, Gerhard Florian Schroff, Hartwig Adam, Georgios Papandreou
  • Publication number: 20200175375
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for instance segmentation. In one aspect, a system generates: (i) data identifying one or more regions of the image, wherein an object is depicted in each region, (ii) for each region, a predicted type of object that is depicted in the region, and (iii) feature channels comprising a plurality of semantic channels and one or more direction channels. The system generates a region descriptor for each of the one or more regions, and provides the region descriptor for each of the one or more regions to a segmentation neural network that processes a region descriptor for a region to generate a predicted segmentation of the predicted type of object depicted in the region.
    Type: Application
    Filed: November 14, 2018
    Publication date: June 4, 2020
    Inventors: Liang-Chieh Chen, Alexander Hermans, Georgios Papandreou, Gerhard Florian Schroff, Peng Wang, Hartwig Adam
  • Publication number: 20190370648
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes obtaining training data for a dense image prediction task; and determining an architecture for a neural network configured to perform the dense image prediction task, comprising: searching a space of candidate architectures to identify one or more best performing architectures using the training data, wherein each candidate architecture in the space of candidate architectures comprises (i) the same first neural network backbone that is configured to receive an input image and to process the input image to generate a plurality of feature maps and (ii) a different dense prediction cell configured to process the plurality of feature maps and to generate an output for the dense image prediction task; and determining the architecture for the neural network based on the best performing candidate architectures.
    Type: Application
    Filed: May 29, 2019
    Publication date: December 5, 2019
    Inventors: Barret Zoph, Jonathon Shlens, Yukun Zhu, Maxwell Donald Emmet Collins, Liang-Chieh Chen, Gerhard Florian Schroff, Hartwig Adam, Georgios Papandreou
  • Patent number: 7622145
    Abstract: Processes for coating implantable medical devices that improve the stability of therapeutic agents contained within the coating.
    Type: Grant
    Filed: July 26, 2005
    Date of Patent: November 24, 2009
    Assignee: Cordis Corporation
    Inventors: Eugena A. Akerman, Dirk Cleeren, Gerard Llanos, Cynthia A. Maryanoff, Georgios Papandreou, William Rion, Karel Six, Thomas L. Todd
  • Publication number: 20060024426
    Abstract: Processes for coating implantable medical devices that improve the stability of therapeutic agents contained within the coating.
    Type: Application
    Filed: July 26, 2005
    Publication date: February 2, 2006
    Inventors: Eugena Akerman, Dirk Cleeren, Gerard Llanos, Cynthia Maryanoff, Georgios Papandreou, William Rion, Karel Six, Thomas Todd