Patents by Inventor Feitong Tan

Feitong Tan 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: 20240290025
    Abstract: A method comprises receiving a first sequence of images of a portion of a user, the first sequence of images being monocular images; generating an avatar based on the first sequence of images, the avatar being based on a model including a feature vector associated with a vertex; receiving a second sequence of images of the portion of the user; and based on the second sequence of images, modifying the avatar with a displacement of the vertex to represent a gesture of the avatar.
    Type: Application
    Filed: February 27, 2024
    Publication date: August 29, 2024
    Inventors: Yinda Zhang, Sean Ryan Francesco Fanello, Ziqian Bai, Feitong Tan, Zeng Huang, Kripasindhu Sarkar, Danhang Tang, Di Qiu, Abhimitra Meka, Ruofei Du, Mingsong Dou, Sergio Orts Escolano, Rohit Kumar Pandey, Thabo Beeler
  • Publication number: 20240212325
    Abstract: Systems and methods for training models to predict dense correspondences across images such as human images. A model may be trained using synthetic training data created from one or more 3D computer models of a subject. In addition, one or more geodesic distances derived from the surfaces of one or more of the 3D models may be used to generate one or more loss values, which may in turn be used in modifying the model's parameters during training.
    Type: Application
    Filed: March 6, 2024
    Publication date: June 27, 2024
    Inventors: Yinda Zhang, Feitong Tan, Danhang Tang, Mingsong Dou, Kaiwen Guo, Sean Ryan Francesco Fanello, Sofien Bouaziz, Cem Keskin, Ruofei Du, Rohit Kumar Pandey, Deqing Sun
  • Patent number: 11954899
    Abstract: Systems and methods for training models to predict dense correspondences across images such as human images. A model may be trained using synthetic training data created from one or more 3D computer models of a subject. In addition, one or more geodesic distances derived from the surfaces of one or more of the 3D models may be used to generate one or more loss values, which may in turn be used in modifying the model's parameters during training.
    Type: Grant
    Filed: March 11, 2021
    Date of Patent: April 9, 2024
    Assignee: GOOGLE LLC
    Inventors: Yinda Zhang, Feitong Tan, Danhang Tang, Mingsong Dou, Kaiwen Guo, Sean Ryan Francesco Fanello, Sofien Bouaziz, Cem Keskin, Ruofei Du, Rohit Kumar Pandey, Deqing Sun
  • Publication number: 20240046618
    Abstract: Systems and methods for training models to predict dense correspondences across images such as human images. A model may be trained using synthetic training data created from one or more 3D computer models of a subject. In addition, one or more geodesic distances derived from the surfaces of one or more of the 3D models may be used to generate one or more loss values, which may in turn be used in modifying the model's parameters during training.
    Type: Application
    Filed: March 11, 2021
    Publication date: February 8, 2024
    Inventors: Yinda Zhang, Feitong Tan, Danhang Tang, Mingsong Dou, Kaiwen Guo, Sean Ryan Francesco Fanello, Sofien Bouaziz, Cem Keskin, Ruofei Du, Rohit Kumar Pandey, Deqing Sun
  • Publication number: 20240020915
    Abstract: Techniques include introducing a neural generator configured to produce novel faces that can be rendered at free camera viewpoints (e.g., at any angle with respect to the camera) and relit under an arbitrary high dynamic range (HDR) light map. A neural implicit intrinsic field takes a randomly sampled latent vector as input and produces as output per-point albedo, volume density, and reflectance properties for any queried 3D location. These outputs are aggregated via a volumetric rendering to produce low resolution albedo, diffuse shading, specular shading, and neural feature maps. The low resolution maps are then upsampled to produce high resolution maps and input into a neural renderer to produce relit images.
    Type: Application
    Filed: July 17, 2023
    Publication date: January 18, 2024
    Inventors: Yinda Zhang, Feitong Tan, Sean Ryan Francesco Fanello, Abhimitra Meka, Sergio Orts Escolano, Danhang Tang, Rohit Kumar Pandey, Jonathan James Taylor