公开(公告)号：US11790550B2

公开(公告)日：2023-10-17

申请号：US17292647

申请日：2020-07-08

Applicant: Google LLC

Inventor： Taihong Xiao ,  Deqing Sun ,  Ming-Hsuan Yang ,  Qifei Wang ,  Jinwei Yuan

IPC: G06K9/00 ,  G06T7/593 ,  G06T7/215

CPC classification number: G06T7/593 ,  G06T7/215 ,  G06T2207/10012 ,  G06T2207/20081

Abstract: A method includes obtaining a first plurality of feature vectors associated with a first image and a second plurality of feature vectors associated with a second image. The method also includes generating a plurality of transformed feature vectors by transforming each respective feature vector of the first plurality of feature vectors by a kernel matrix trained to define an elliptical inner product space. The method additionally includes generating a cost volume by determining, for each respective transformed feature vector of the plurality of transformed feature vectors, a plurality of inner products, wherein each respective inner product of the plurality of inner products is between the respective transformed feature vector and a corresponding candidate feature vector of a corresponding subset of the second plurality of feature vectors. The method further includes determining, based on the cost volume, a pixel correspondence between the first image and the second image.

公开(公告)号：US20220189051A1

公开(公告)日：2022-06-16

申请号：US17292647

申请日：2020-07-08

Applicant: Google LLC

Inventor： Taihong Xiao ,  Deqing Sun ,  Ming-Hsuan Yang ,  Qifei Wang ,  Jinwei Yuan

IPC: G06T7/593 ,  G06T7/215

Abstract: A method includes obtaining a first plurality of feature vectors associated with a first image and a second plurality of feature vectors associated with a second image. The method also includes generating a plurality of transformed feature vectors by transforming each respective feature vector of the first plurality of feature vectors by a kernel matrix trained to define an elliptical inner product space. The method additionally includes generating a cost volume by determining, for each respective transformed feature vector of the plurality of transformed feature vectors, a plurality of inner products, wherein each respective inner product of the plurality of inner products is between the respective transformed feature vector and a corresponding candidate feature vector of a corresponding subset of the second plurality of feature vectors. The method further includes determining, based on the cost volume, a pixel correspondence between the first image and the second image.