Subdividing a three-dimensional mesh utilizing a neural network

    公开(公告)号:US12118669B2

    公开(公告)日:2024-10-15

    申请号:US17821704

    申请日:2022-08-23

    Applicant: Adobe Inc.

    CPC classification number: G06T17/20 G06N3/02 G06N3/08 G06T7/13 G06T2207/20081

    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.

    SUBDIVIDING A THREE-DIMENSIONAL MESH UTILIZING A NEURAL NETWORK

    公开(公告)号:US20230267686A1

    公开(公告)日:2023-08-24

    申请号:US17821704

    申请日:2022-08-23

    Applicant: Adobe Inc.

    CPC classification number: G06T17/20 G06N3/08 G06T7/13 G06N3/02 G06T2207/20081

    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.

    Subdividing a three-dimensional mesh utilizing a neural network

    公开(公告)号:US11423617B2

    公开(公告)日:2022-08-23

    申请号:US16863189

    申请日:2020-04-30

    Applicant: Adobe Inc.

    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.

    Decimating a three-dimensional mesh via successive self-parameterization

    公开(公告)号:US11257290B2

    公开(公告)日:2022-02-22

    申请号:US16863099

    申请日:2020-04-30

    Applicant: Adobe Inc.

    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.

    DECIMATING A THREE-DIMENSIONAL MESH VIA SUCCESSIVE SELF-PARAMETERIZATION

    公开(公告)号:US20210343082A1

    公开(公告)日:2021-11-04

    申请号:US16863099

    申请日:2020-04-30

    Applicant: Adobe Inc.

    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.

    SUBDIVIDING A THREE-DIMENSIONAL MESH UTILIZING A NEURAL NETWORK

    公开(公告)号:US20210343080A1

    公开(公告)日:2021-11-04

    申请号:US16863189

    申请日:2020-04-30

    Applicant: Adobe Inc.

    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.

Patent Agency Ranking