公开(公告)号：US11704844B2

公开(公告)日：2023-07-18

申请号：US17722969

申请日：2022-04-18

Applicant: Google LLC

Inventor： Daniel Christopher Duckworth ,  Alexey Dosovitskiy ,  Ricardo Martin Brualla ,  Jonathan Tilton Barron ,  Noha Waheed Ahmed Radwan ,  Seyed Mohammad Mehdi Sajjadi

IPC: G06T11/00 ,  G06T7/90

CPC classification number: G06T11/001 ,  G06T7/90 ,  G06T2207/20081

Abstract: Provided are systems and methods for synthesizing novel views of complex scenes (e.g., outdoor scenes). In some implementations, the systems and methods can include or use machine-learned models that are capable of learning from unstructured and/or unconstrained collections of imagery such as, for example, “in the wild” photographs. In particular, example implementations of the present disclosure can learn a volumetric scene density and radiance represented by a machine-learned model such as one or more multilayer perceptrons (MLPs).

公开(公告)号：US20220036602A1

公开(公告)日：2022-02-03

申请号：US17390263

申请日：2021-07-30

Applicant: Google LLC

Inventor： Daniel Christopher Duckworth ,  Seyed Mohammad Mehdi Sajjadi ,  Jonathan Tilton Barron ,  Noha Waheed Ahmed Radwan ,  Alexey Dosovitskiy ,  Ricardo Martin-Brualla

IPC: G06T11/00 ,  G06T7/90

Abstract: Provided are systems and methods for synthesizing novel views of complex scenes (e.g., outdoor scenes). In some implementations, the systems and methods can include or use machine-learned models that are capable of learning from unstructured and/or unconstrained collections of imagery such as, for example, “in the wild” photographs. In particular, example implementations of the present disclosure can learn a volumetric scene density and radiance represented by a machine-learned model such as one or more multilayer perceptrons (MLPs).

公开(公告)号：US20220237834A1

公开(公告)日：2022-07-28

申请号：US17722969

申请日：2022-04-18

Applicant: Google LLC

Inventor： Daniel Christopher Duckworth ,  Alexey Dosovitskiy ,  Ricardo Martin Brualla ,  Jonathan Tilton Barron ,  Noha Waheed Ahmed Radwan ,  Seyed Mohammad Mehdi Sajjadi

IPC: G06T11/00 ,  G06T7/90

Abstract: Provided are systems and methods for synthesizing novel views of complex scenes (e.g., outdoor scenes). In some implementations, the systems and methods can include or use machine-learned models that are capable of learning from unstructured and/or unconstrained collections of imagery such as, for example, “in the wild” photographs. In particular, example implementations of the present disclosure can learn a volumetric scene density and radiance represented by a machine-learned model such as one or more multilayer perceptrons (MLPs).