Patents by Inventor Hsueh-ti Liu

Hsueh-ti Liu 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: 20250073590
    Abstract: Some implementations relate to methods, systems and computer readable media to provide an aerodynamic force model for real-time distributed physics simulation. According to one aspect, a computer-implemented method includes receiving a description of a mechanism that includes physically coupled geometric assemblies within a virtual experience, with each geometric assembly defining a surface mesh. The description includes motion data of the mechanism. The method further includes, for each geometric assembly, identifying exposed surface areas of the surface mesh. The method further includes evaluating an aerodynamic force model based on the exposed surface areas and the motion data of the mechanism, where the aerodynamic force model includes a pressure coefficient that varies based on an angle of attack and based on windward and leeward facing surfaces. The method further includes integrating the aerodynamic force models into a physics simulation to refine the motion data of the mechanism.
    Type: Application
    Filed: August 28, 2024
    Publication date: March 6, 2025
    Applicant: Roblox Corporation
    Inventors: Milad Rakhsha, Xiaoting Zhang, Maciej Mizerski, Jun Kudo, Wei-Ting Liao, Alexander Polyakov, Kyle Khem Chand, Hsueh-Ti Liu
  • Patent number: 12118669
    Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing one or more neural networks to recursively subdivide a three-dimensional mesh according to local geometries of vertices in the three-dimensional mesh. For example, the disclosed system can determine a local geometry (e.g., a one-ring neighborhood of half-flaps) for each vertex in a three-dimensional mesh. For each subdivision iteration, the disclosed system can then utilize a neural network to determine displacement coordinates for existing vertices in the three-dimensional mesh and coordinates for new vertices added to edges between the existing vertices in the three-dimensional mesh in accordance with the local geometries of the existing vertices. Furthermore, the disclosed system can generate a subdivided three-dimensional mesh based on the determined displacement coordinates for the existing vertices and the determined coordinates for the new vertices.
    Type: Grant
    Filed: August 23, 2022
    Date of Patent: October 15, 2024
    Assignee: Adobe Inc.
    Inventors: Vladimir Kim, Siddhartha Chaudhuri, Noam Aigerman, Hsueh-ti Liu, Alec Jacobson
  • Publication number: 20230267686
    Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing one or more neural networks to recursively subdivide a three-dimensional mesh according to local geometries of vertices in the three-dimensional mesh. For example, the disclosed system can determine a local geometry (e.g., a one-ring neighborhood of half-flaps) for each vertex in a three-dimensional mesh. For each subdivision iteration, the disclosed system can then utilize a neural network to determine displacement coordinates for existing vertices in the three-dimensional mesh and coordinates for new vertices added to edges between the existing vertices in the three-dimensional mesh in accordance with the local geometries of the existing vertices. Furthermore, the disclosed system can generate a subdivided three-dimensional mesh based on the determined displacement coordinates for the existing vertices and the determined coordinates for the new vertices.
    Type: Application
    Filed: August 23, 2022
    Publication date: August 24, 2023
    Inventors: Vladimir Kim, Siddhartha Chaudhuri, Noam Aigerman, Hsueh-ti Liu, Alec Jacobson
  • Patent number: 11423617
    Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing one or more neural networks to recursively subdivide a three-dimensional mesh according to local geometries of vertices in the three-dimensional mesh. For example, the disclosed system can determine a local geometry (e.g., a one-ring neighborhood of half-flaps) for each vertex in a three-dimensional mesh. For each subdivision iteration, the disclosed system can then utilize a neural network to determine displacement coordinates for existing vertices in the three-dimensional mesh and coordinates for new vertices added to edges between the existing vertices in the three-dimensional mesh in accordance with the local geometries of the existing vertices. Furthermore, the disclosed system can generate a subdivided three-dimensional mesh based on the determined displacement coordinates for the existing vertices and the determined coordinates for the new vertices.
    Type: Grant
    Filed: April 30, 2020
    Date of Patent: August 23, 2022
    Assignee: Adobe Inc.
    Inventors: Vladimir Kim, Siddhartha Chaudhuri, Noam Aigerman, Hsueh-ti Liu, Alec Jacobson
  • Patent number: 11257290
    Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for iteratively decimating a three-dimensional mesh utilizing successive self-parameterization. For example, the disclosed system can self-parameterize local geometries of a three-dimensional mesh using surface mappings within a two-dimensional surface mapping space. The disclosed system can collapse edges in the three-dimensional mesh to create new vertices from the collapsed edges. The disclosed system can parameterize the collapsed edges based on the surface mappings to collapse corresponding edges within the surface mapping space. The disclosed system can thus generate a decimated three-dimensional mesh by collapsing edges in the three-dimensional mesh while providing a bijective map between points in the decimated three-dimensional mesh and corresponding points in the three-dimensional mesh.
    Type: Grant
    Filed: April 30, 2020
    Date of Patent: February 22, 2022
    Assignee: Adobe Inc.
    Inventors: Vladimir Kim, Siddhartha Chaudhuri, Noam Aigerman, Hsueh-ti Liu, Alec Jacobson
  • Publication number: 20210343080
    Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing one or more neural networks to recursively subdivide a three-dimensional mesh according to local geometries of vertices in the three-dimensional mesh. For example, the disclosed system can determine a local geometry (e.g., a one-ring neighborhood of half-flaps) for each vertex in a three-dimensional mesh. For each subdivision iteration, the disclosed system can then utilize a neural network to determine displacement coordinates for existing vertices in the three-dimensional mesh and coordinates for new vertices added to edges between the existing vertices in the three-dimensional mesh in accordance with the local geometries of the existing vertices. Furthermore, the disclosed system can generate a subdivided three-dimensional mesh based on the determined displacement coordinates for the existing vertices and the determined coordinates for the new vertices.
    Type: Application
    Filed: April 30, 2020
    Publication date: November 4, 2021
    Inventors: Vladimir Kim, Siddhartha Chaudhuri, Noam Aigerman, Hsueh-ti Liu, Alec Jacobson
  • Publication number: 20210343082
    Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for iteratively decimating a three-dimensional mesh utilizing successive self-parameterization. For example, the disclosed system can self-parameterize local geometries of a three-dimensional mesh using surface mappings within a two-dimensional surface mapping space. The disclosed system can collapse edges in the three-dimensional mesh to create new vertices from the collapsed edges. The disclosed system can parameterize the collapsed edges based on the surface mappings to collapse corresponding edges within the surface mapping space. The disclosed system can thus generate a decimated three-dimensional mesh by collapsing edges in the three-dimensional mesh while providing a bijective map between points in the decimated three-dimensional mesh and corresponding points in the three-dimensional mesh.
    Type: Application
    Filed: April 30, 2020
    Publication date: November 4, 2021
    Inventors: Vladimir Kim, Siddhartha Chaudhuri, Noam Aigerman, Hsueh-ti Liu, Alec Jacobson