公开(公告)号：US20240212325A1

公开(公告)日：2024-06-27

申请号：US18596822

申请日：2024-03-06

Applicant: Google LLC

Inventor： 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

IPC: G06V10/771 ,  G06T7/70 ,  G06T17/00 ,  G06V10/44 ,  G06V10/75

CPC classification number: G06V10/771 ,  G06T7/70 ,  G06T17/00 ,  G06V10/44 ,  G06V10/751 ,  G06T2207/20081 ,  G06T2207/20084

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.

公开(公告)号：US11954899B2

公开(公告)日：2024-04-09

申请号：US18274371

申请日：2021-03-11

Applicant: Google LLC

Inventor： 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

IPC: G06V10/771 ,  G06T7/70 ,  G06T17/00 ,  G06V10/44 ,  G06V10/75

CPC classification number: G06V10/771 ,  G06T7/70 ,  G06T17/00 ,  G06V10/44 ,  G06V10/751 ,  G06T2207/20081 ,  G06T2207/20084

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.

公开(公告)号：US20240046618A1

公开(公告)日：2024-02-08

申请号：US18274371

申请日：2021-03-11

Applicant: Google LLC

Inventor： 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

IPC: G06V10/771 ,  G06T17/00 ,  G06T7/70 ,  G06V10/44 ,  G06V10/75

CPC classification number: G06V10/771 ,  G06T17/00 ,  G06T7/70 ,  G06V10/44 ,  G06V10/751 ,  G06T2207/20081 ,  G06T2207/20084

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.

公开(公告)号：US12066282B2

公开(公告)日：2024-08-20

申请号：US17413847

申请日：2020-11-11

Applicant: GOOGLE LLC

Inventor： Sean Ryan Francesco Fanello ,  Kaiwen Guo ,  Peter Christopher Lincoln ,  Philip Lindsley Davidson ,  Jessica L. Busch ,  Xueming Yu ,  Geoffrey Harvey ,  Sergio Orts Escolano ,  Rohit Kumar Pandey ,  Jason Dourgarian ,  Danhang Tang ,  Adarsh Prakash Murthy Kowdle ,  Emily B. Cooper ,  Mingsong Dou ,  Graham Fyffe ,  Christoph Rhemann ,  Jonathan James Taylor ,  Shahram Izadi ,  Paul Ernest Debevec

IPC: G01B11/25 ,  G01B11/245 ,  G06T15/50 ,  G06T17/20

CPC classification number: G01B11/2513 ,  G01B11/245 ,  G06T15/506 ,  G06T17/205

Abstract: A lighting stage includes a plurality of lights that project alternating spherical color gradient illumination patterns onto an object or human performer at a predetermined frequency. The lighting stage also includes a plurality of cameras that capture images of an object or human performer corresponding to the alternating spherical color gradient illumination patterns. The lighting stage also includes a plurality of depth sensors that capture depth maps of the object or human performer at the predetermined frequency. The lighting stage also includes (or is associated with) one or more processors that implement a machine learning algorithm to produce a three-dimensional (3D) model of the object or human performer. The 3D model includes relighting parameters used to relight the 3D model under different lighting conditions.

公开(公告)号：US20220065620A1

公开(公告)日：2022-03-03

申请号：US17413847

申请日：2020-11-11

Applicant: GOOGLE LLC

Inventor： Sean Ryan Francesco Fanello ,  Kaiwen Guo ,  Peter Christopher Lincoln ,  Philip Lindsley Davidson ,  Jessica L. Busch ,  Xueming Yu ,  Geoffrey Harvey ,  Sergio Orts Escolano ,  Rohit Kumar Pandey ,  Jason Dourgarian ,  Danhang Tang ,  Adarsh Prakash Murthy Kowdle ,  Emily B. Cooper ,  Mingsong Dou ,  Graham Fyffe ,  Christoph Rhemann ,  Jonathan James Taylor ,  Shahram Izadi ,  Paul Ernest Debevec

IPC: G01B11/25 ,  G06T15/50 ,  G01B11/245 ,  G06T17/20

Abstract: A lighting stage includes a plurality of lights that project alternating spherical color gradient illumination patterns onto an object or human performer at a predetermined frequency. The lighting stage also includes a plurality of cameras that capture images of an object or human performer corresponding to the alternating spherical color gradient illumination patterns. The lighting stage also includes a plurality of depth sensors that capture depth maps of the object or human performer at the predetermined frequency. The lighting stage also includes (or is associated with) one or more processors that implement a machine learning algorithm to produce a three-dimensional (3D) model of the object or human performer. The 3D model includes relighting parameters used to relight the 3D model under different lighting conditions.