公开(公告)号：US20230169727A1

公开(公告)日：2023-06-01

申请号：US17922160

申请日：2020-04-30

Applicant: Google LLC

Inventor： Cristian Sminchisescu ,  Hongyi Xu ,  Eduard Gabriel Bazavan ,  Andrei Zanfir ,  William T. Freeman ,  Rahul Sukthankar

IPC: G06T17/20 ,  G06T19/20 ,  G06N3/08 ,  G06N3/0455

CPC classification number: G06T17/20 ,  G06T19/20 ,  G06N3/08 ,  G06N3/0455 ,  G06T2219/2021

Abstract: The present disclosure provides a statistical, articulated 3D human shape modeling pipeline within a fully trainable, modular, deep learning framework. In particular, aspects of the present disclosure are directed to a machine-learned 3D human shape model with at least facial and body shape components that are jointly trained end-to-end on a set of training data. Joint training of the model components (e.g., including both facial, hands, and rest of body components) enables improved consistency of synthesis between the generated face and body shapes.

公开(公告)号：US12249030B2

公开(公告)日：2025-03-11

申请号：US17922160

申请日：2020-04-30

Applicant: Google LLC

Inventor： Cristian Sminchisescu ,  Hongyi Xu ,  Eduard Gabriel Bazavan ,  Andrei Zanfir ,  William T. Freeman ,  Rahul Sukthankar

IPC: G06T17/20 ,  G06N3/0455 ,  G06N3/08 ,  G06T19/20

Abstract: The present disclosure provides a statistical, articulated 3D human shape modeling pipeline within a fully trainable, modular, deep learning framework. In particular, aspects of the present disclosure are directed to a machine-learned 3D human shape model with at least facial and body shape components that are jointly trained end-to-end on a set of training data. Joint training of the model components (e.g., including both facial, hands, and rest of body components) enables improved consistency of synthesis between the generated face and body shapes.

公开(公告)号：US20240161470A1

公开(公告)日：2024-05-16

申请号：US18549617

申请日：2021-04-21

Applicant: Google LLC

Inventor： Cristian Sminchisescu ,  Thiemo Andreas Alldieck ,  Hongyi Xu

IPC: G06V10/774 ,  G06T7/50 ,  G06T15/80 ,  G06T17/20 ,  G06V10/26 ,  G06V10/776 ,  G06V20/64 ,  G06V20/70 ,  G06V40/10

CPC classification number: G06V10/774 ,  G06T7/50 ,  G06T15/80 ,  G06T17/20 ,  G06V10/26 ,  G06V10/776 ,  G06V20/64 ,  G06V20/70 ,  G06V40/10 ,  G06T2200/04

Abstract: Systems and methods of the present disclosure are directed to a computer-implemented method for training a machine-learned model for implicit representation of an object. The method can include obtaining a latent code descriptive of a shape of an object comprising one or more object segments. The method can include determining spatial query points. The method can include processing the latent code and spatial query points with segment representation portions of a machine-learned implicit object representation model to obtain implicit segment representations for the object segments. The method can include determining an implicit object representation of the object and semantic data. The method can include evaluating a loss function. The method can include adjusting parameters of the machine-learned implicit object representation model based at least in part on the loss function.