公开(公告)号：US12249031B2

公开(公告)日：2025-03-11

申请号：US18390173

申请日：2023-12-20

Applicant: 3SHAPE A/S

Inventor： Jens Peter Träff ,  Jens Christian Jørgensen ,  Alejandro Alonso Diaz ,  Mathias Bøgh Stokholm ,  Asger Vejen Hoedt

IPC: G06T17/00 ,  A61C7/00 ,  A61C9/00 ,  A61C13/00 ,  G06T7/00 ,  G06T9/00 ,  G06T11/00 ,  G06T17/20 ,  G06T19/20 ,  G06V10/774 ,  G16H30/40

Abstract: A computer-implemented method for generating a 2D or 3D object, including training an autoencoder on a first set of training data to identify a first set of latent variables and generate a first set of output data; training an hourglass predictor on a second set of training data, where the hourglass predictor encoder converts a set of related but different training input data to a second set of latent variables, which decode into a second set of output data of the same type as the first set of output data; and using the hourglass predictor to predict a 2D or 3D object of the same type as the first set of output data based on a 2D or 3D object of the same type as the second set of input data.

公开(公告)号：US11887209B2

公开(公告)日：2024-01-30

申请号：US17434205

申请日：2020-02-25

Applicant: 3SHAPE A/S

Inventor： Jens Peter Träff ,  Jens Christian Jørgensen ,  Alejandro Alonso Diaz ,  Mathias Bøgh Stokholm ,  Asger Vejen Hoedt

IPC: G06T17/20 ,  G06T17/00 ,  G16H30/40 ,  G06V10/774 ,  A61C7/00 ,  A61C9/00 ,  A61C13/00 ,  G06T7/00 ,  G06T9/00 ,  G06T11/00 ,  G06T19/20

CPC classification number: G06T17/20 ,  A61C7/002 ,  A61C9/0053 ,  A61C13/0004 ,  A61C13/0019 ,  G06T7/0012 ,  G06T9/002 ,  G06T11/00 ,  G06T17/00 ,  G06T19/20 ,  G06V10/7747 ,  G16H30/40 ,  G06T2207/30036 ,  G06T2210/41 ,  G06T2219/2021

Abstract: A computer-implemented method for generating a 2D or 3D object, including training an autoencoder on a first set of training data to identify a first set of latent variables and generate a first set of output data; training an hourglass predictor on a second set of training data, where the hourglass predictor encoder converts a set of related but different training input data to a second set of latent variables, which decode into a second set of output data of the same type as the first set of output data; and using the hourglass predictor to predict a 2D or 3D object of the same type as the first set of output data based on a 2D or 3D object of the same type as the second set of input data.