公开(公告)号：US20230130281A1

公开(公告)日：2023-04-27

申请号：US17551724

申请日：2021-12-15

Applicant: Google LLC

Inventor： Matthew Alun Brown ,  Ricardo Martin-Brualla ,  Keunhong Park ,  Christopher Derming Xie

IPC: G06V10/774 ,  G06N3/02 ,  G06T17/00 ,  G06V10/776 ,  G06T7/194 ,  G06V10/82

Abstract: Systems and methods for three-dimensional object category modeling can utilize figure-ground neural radiance fields for unsupervised training and inference. For example, the systems and methods can include a foreground model and a background model that can generate an object output based at least in part on one or more learned embeddings. The foreground model and background model may process position data and view direction data in order to output color data and volume density data for a respective position and view direction. Moreover, the object category model may be trained to generate an object output, which may include an instance interpolation, a view synthesis, or a segmentation.

公开(公告)号：US12026892B2

公开(公告)日：2024-07-02

申请号：US17551724

申请日：2021-12-15

Applicant: Google LLC

Inventor： Matthew Alun Brown ,  Ricardo Martin-Brualla ,  Keunhong Park ,  Christopher Derming Xie

IPC: G06T7/194 ,  G06T17/00

CPC classification number: G06T7/194 ,  G06T17/00 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Systems and methods for three-dimensional object category modeling can utilize figure-ground neural radiance fields for unsupervised training and inference. For example, the systems and methods can include a foreground model and a background model that can generate an object output based at least in part on one or more learned embeddings. The foreground model and background model may process position data and view direction data in order to output color data and volume density data for a respective position and view direction. Moreover, the object category model may be trained to generate an object output, which may include an instance interpolation, a view synthesis, or a segmentation.

公开(公告)号：US11853892B2

公开(公告)日：2023-12-26

申请号：US17252663

申请日：2019-07-10

Applicant: Google LLC

Inventor： Matthew Alun Brown ,  Jonathan Chung-Kuan Huang ,  Tal Remez

IPC: G06T7/194 ,  G06T7/11 ,  G06T11/20 ,  G06V10/764 ,  G06V10/82 ,  G06N3/084 ,  G06N3/045

CPC classification number: G06N3/084 ,  G06N3/045 ,  G06T7/11 ,  G06T7/194 ,  G06T11/20 ,  G06V10/764 ,  G06V10/82 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2210/12

Abstract: Example aspects of the present disclosure are directed to systems and methods that enable weakly-supervised learning of instance segmentation by applying a cut-and-paste technique to training of a generator model included in a generative adversarial network. In particular, the present disclosure provides a weakly-supervised approach to object instance segmentation. In some implementations, starting with known or predicted object bounding boxes, a generator model can learn to generate object masks by playing a game of cut-and-paste in an adversarial learning setup.

公开(公告)号：US20240303825A1

公开(公告)日：2024-09-12

申请号：US18669733

申请日：2024-05-21

Applicant: Google LLC

Inventor： Matthew Alun Brown ,  Ricardo Martin-Brualla ,  Keunhong Park ,  Christopher Derming Xie

IPC: G06T7/194 ,  G06T17/00

CPC classification number: G06T7/194 ,  G06T17/00 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Systems and methods for three-dimensional object category modeling can utilize figure-ground neural radiance fields for unsupervised training and inference. For example, the systems and methods can include a foreground model and a background model that can generate an object output based at least in part on one or more learned embeddings. The foreground model and background model may process position data and view direction data in order to output color data and volume density data for a respective position and view direction. Moreover, the object category model may be trained to generate an object output, which may include an instance interpolation, a view synthesis, or a segmentation.

公开(公告)号：US20210256707A1

公开(公告)日：2021-08-19

申请号：US17252663

申请日：2019-07-10

Applicant: Google LLC

Inventor： Matthew Alun Brown ,  Jonathan Chung-Kuan Huang ,  Tal Remez

IPC: G06T7/194 ,  G06N3/04 ,  G06T7/11 ,  G06T11/20

Abstract: Example aspects of the present disclosure are directed to systems and methods that enable weakly-supervised learning of instance segmentation by applying a cut-and-paste technique to training of a generator model included in a generative adversarial network. In particular, the present disclosure provides a weakly-supervised approach to object instance segmentation. In some implementations, starting with known or predicted object bounding boxes, a generator model can learn to generate object masks by playing a game of cut-and-paste in an adversarial learning setup.