公开(公告)号：US12106428B2

公开(公告)日：2024-10-01

申请号：US17686683

申请日：2022-03-04

申请人： Google LLC

发明人： Konstantinos Rematas ,  Thomas Allen Funkhouser ,  Vittorio Carlo Ferrari ,  Andrew Huaming Liu ,  Andrea Tagliasacchi ,  Pratul Preeti Srinivasan ,  Jonathan Tilton Barron

IPC分类号： G06T15/20 ,  G06N20/00 ,  G06T5/50 ,  G06T5/92 ,  G06T17/10

CPC分类号： G06T15/205 ,  G06N20/00 ,  G06T5/50 ,  G06T5/92 ,  G06T17/10

摘要： Systems and methods for view synthesis and three-dimensional reconstruction can learn an environment by utilizing a plurality of images of an environment and depth data. The use of depth data can be helpful when the quantity of images and different angles may be limited. For example, large outdoor environments can be difficult to learn due to the size, the varying image exposures, and the limited variance in view direction changes. The systems and methods can leverage a plurality of panoramic images and corresponding lidar data to accurately learn a large outdoor environment to then generate view synthesis outputs and three-dimensional reconstruction outputs. Training may include the use of an exposure correction network to address lighting exposure differences between training images.

公开(公告)号：US20230281913A1

公开(公告)日：2023-09-07

申请号：US17686683

申请日：2022-03-04

申请人： Google LLC

发明人： Konstantinos Rematas ,  Thomas Allen Funkhouser ,  Vittorio Carlo Ferrari ,  Andrew Huaming Liu ,  Andrea Tagliasacchi ,  Pratul Preeti Srinivasan ,  Jonathan Tilton Barron

IPC分类号： G06T15/20 ,  G06T17/10 ,  G06N20/00 ,  G06T5/50 ,  G06T5/00

CPC分类号： G06T15/205 ,  G06T17/10 ,  G06N20/00 ,  G06T5/50 ,  G06T5/009

摘要： Systems and methods for view synthesis and three-dimensional reconstruction can learn an environment by utilizing a plurality of images of an environment and depth data. The use of depth data can be helpful when the quantity of images and different angles may be limited. For example, large outdoor environments can be difficult to learn due to the size, the varying image exposures, and the limited variance in view direction changes. The systems and methods can leverage a plurality of panoramic images and corresponding lidar data to accurately learn a large outdoor environment to then generate view synthesis outputs and three-dimensional reconstruction outputs. Training may include the use of an exposure correction network to address lighting exposure differences between training images.