公开(公告)号：US20170124433A1

公开(公告)日：2017-05-04

申请号：US15342766

申请日：2016-11-03

Applicant: NEC Laboratories America, Inc.

Inventor： Manmohan Chandraker ,  Angjoo Kim

IPC: G06K9/66 ,  G06N3/04 ,  G06F17/30 ,  G06N3/08 ,  G06K9/62 ,  G06K9/46

CPC classification number: G06N3/04 ,  G06F17/30247 ,  G06N3/0454 ,  G06T7/337 ,  G06T7/50 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A computer-implemented method for training a deep learning network is presented. The method includes receiving a first image and a second image, mining exemplar thin-plate spline (TPS) to determine transformations for generating point correspondences between the first and second images, using artificial point correspondences to train the deep neural network, learning and using the TPS transformation output through a spatial transformer, and applying heuristics for selecting an acceptable set of images to match for accurate reconstruction. The deep learning network learns to warp points in the first image to points in the second image.

公开(公告)号：US10204299B2

公开(公告)日：2019-02-12

申请号：US15342766

申请日：2016-11-03

Applicant: NEC Laboratories America, Inc.

Inventor： Manmohan Chandraker ,  Angjoo Kim

IPC: G06K9/00 ,  G06N3/04 ,  G06F17/30 ,  G06T7/33 ,  G06T7/50

Abstract: A computer-implemented method for training a deep learning network is presented. The method includes receiving a first image and a second image, mining exemplar thin-plate spline (TPS) to determine transformations for generating point correspondences between the first and second images, using artificial point correspondences to train the deep neural network, learning and using the TPS transformation output through a spatial transformer, and applying heuristics for selecting an acceptable set of images to match for accurate reconstruction. The deep learning network learns to warp points in the first image to points in the second image.