公开(公告)号：US08661053B2

公开(公告)日：2014-02-25

申请号：US13674483

申请日：2012-11-12

Applicant: Google Inc.

Inventor： John Flynn ,  Dragomir Anguelov ,  Hartmut Neven ,  Mark Cummins ,  James Philbin ,  Rafael Spring ,  Hartwig Adam ,  Anand Pillai

IPC: G06F17/30

CPC classification number: G06F17/30268 ,  G06F17/30247 ,  G06F17/3028

Abstract: A method and apparatus for enabling virtual tags is described. The method may include receiving a first digital image data and virtual tag data to be associated with a real-world object in the first digital image data, wherein the first digital image data is captured by a first mobile device, and the virtual tag data includes metadata received from a user of the first mobile device. The method may also include generating a first digital signature from the first digital image data that describes the real-world object, and in response to the generation, inserting in substantially real-time the first digital signature into a searchable index of digital images. The method may also include storing, in a tag database, the virtual tag data and an association between the virtual tag data and the first digital signature inserted into the index of digital images.

Abstract translation: 描述了一种用于启用虚拟标签的方法和装置。 该方法可以包括在第一数字图像数据中接收与真实世界对象相关联的第一数字图像数据和虚拟标签数据，其中第一数字图像数据由第一移动设备捕获，并且虚拟标签数据包括 从第一移动设备的用户接收的元数据。 该方法还可以包括从描述真实世界对象的第一数字图像数据生成第一数字签名，并且响应于生成，基本上实时地将第一数字签名插入到可搜索的数字图像索引中。 该方法还可以包括在标签数据库中存储虚拟标签数据以及虚拟标签数据与插入数字图像索引中的第一数字签名之间的关联。

公开(公告)号：US20160335795A1

公开(公告)日：2016-11-17

申请号：US15154417

申请日：2016-05-13

Applicant: Google Inc.

Inventor： John Flynn ,  Keith Snavely ,  Ivan Neulander ,  James Philbin

IPC: G06T15/20

CPC classification number: G06T15/20 ,  G06K9/00664 ,  G06K9/4628 ,  G06K9/4652 ,  G06K9/6272 ,  G06N99/005 ,  G06T15/205

Abstract: A system and method of deep learning using deep networks to predict new views from existing images may generate and improve models and representations from large-scale data. This system and method of deep learning may employ a deep architecture performing new view synthesis directly from pixels, trained from large numbers of posed image sets. A system employing this type of deep network may produce pixels of an unseen view based on pixels of neighboring views, lending itself to applications in graphics generation.

Abstract translation: 使用深层网络深入学习从现有图像预测新视图的系统和方法可能会生成并改进大型数据的模型和表示。 这种深度学习的系统和方法可以采用深入的架构，直接从像素中执行新的视图合成，从大量呈现的图像集训练。 采用这种类型的深度网络的系统可以基于相邻视图的像素产生不可见视图的像素，从而将其自身应用于图形生成中。

公开(公告)号：US09916679B2

公开(公告)日：2018-03-13

申请号：US15154417

申请日：2016-05-13

Applicant: Google Inc.

Inventor： John Flynn ,  Keith Snavely ,  Ivan Neulander ,  James Philbin

IPC: G06T15/20 ,  G06K9/00 ,  G06K9/62 ,  G06K9/46

CPC classification number: G06T15/20 ,  G06K9/00664 ,  G06K9/4628 ,  G06K9/4652 ,  G06K9/6272 ,  G06N99/005 ,  G06T15/205

Abstract: A system and method of deep learning using deep networks to predict new views from existing images may generate and improve models and representations from large-scale data. This system and method of deep learning may employ a deep architecture performing new view synthesis directly from pixels, trained from large numbers of posed image sets. A system employing this type of deep network may produce pixels of an unseen view based on pixels of neighboring views, lending itself to applications in graphics generation.