公开(公告)号：US20200349722A1

公开(公告)日：2020-11-05

申请号：US16464608

申请日：2017-12-01

Applicant: Google LLC

Inventor： Cordelia Luise Schmid ,  Sudheendra Vijayanarasimhan ,  Susanna Maria Ricco ,  Bryan Andrew Seybold ,  Rahul Sukthankar ,  Aikaterini Fragkiadaki

IPC: G06T7/269 ,  G06T7/215 ,  G06T7/70 ,  G06N3/04

Abstract: A system comprising an encoder neural network, a scene structure decoder neural network, and a motion decoder neural network. The encoder neural network is configured to: receive a first image and a second image; and process the first image and the second image to generate an encoded representation of the first image and the second image. The scene structure decoder neural network is configured to process the encoded representation to generate a structure output characterizing a structure of a scene depicted in the first image. The motion decoder neural network configured to process the encoded representation to generate a motion output characterizing motion between the first image and the second image.

公开(公告)号：US11763466B2

公开(公告)日：2023-09-19

申请号：US17132623

申请日：2020-12-23

Applicant: Google LLC

Inventor： Cordelia Luise Schmid ,  Sudheendra Vijayanarasimhan ,  Susanna Maria Ricco ,  Bryan Andrew Seybold ,  Rahul Sukthankar ,  Aikaterini Fragkiadaki

IPC: G06T7/269 ,  G06N3/02 ,  G06T3/40 ,  G06T9/00 ,  G06T7/215 ,  G06T7/70 ,  G06N3/045 ,  G06N3/048 ,  G06V10/82 ,  G06V10/44

CPC classification number: G06T7/269 ,  G06N3/045 ,  G06N3/048 ,  G06T7/215 ,  G06T7/70 ,  G06V10/454 ,  G06V10/82 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A system comprising an encoder neural network, a scene structure decoder neural network, and a motion decoder neural network. The encoder neural network is configured to: receive a first image and a second image; and process the first image and the second image to generate an encoded representation of the first image and the second image. The scene structure decoder neural network is configured to process the encoded representation to generate a structure output characterizing a structure of a scene depicted in the first image. The motion decoder neural network configured to process the encoded representation to generate a motion output characterizing motion between the first image and the second image.

公开(公告)号：US20210118153A1

公开(公告)日：2021-04-22

申请号：US17132623

申请日：2020-12-23

Applicant: Google LLC

Inventor： Cordelia Luise Schmid ,  Sudheendra Vijayanarasimhan ,  Susanna Maria Ricco ,  Bryan Andrew Seybold ,  Rahul Sukthankar ,  Aikaterini Fragkiadaki

IPC: G06T7/269 ,  G06N3/04 ,  G06T7/70 ,  G06T7/215

Abstract: A system comprising an encoder neural network, a scene structure decoder neural network, and a motion decoder neural network. The encoder neural network is configured to: receive a first image and a second image; and process the first image and the second image to generate an encoded representation of the first image and the second image. The scene structure decoder neural network is configured to process the encoded representation to generate a structure output characterizing a structure of a scene depicted in the first image. The motion decoder neural network configured to process the encoded representation to generate a motion output characterizing motion between the first image and the second image.