公开(公告)号：US20210065391A1

公开(公告)日：2021-03-04

申请号：US16987705

申请日：2020-08-07

Applicant: NEC Laboratories America, Inc.

Inventor： Quoc-Huy Tran ,  Pan Ji ,  Manmohan Chandraker ,  Lokender Tiwari

IPC: G06T7/579 ,  G06N3/08 ,  G06T15/10 ,  G06T15/00 ,  G06T7/20 ,  G06T7/80

Abstract: A method for improving geometry-based monocular structure from motion (SfM) by exploiting depth maps predicted by convolutional neural networks (CNNs) is presented. The method includes capturing a sequence of RGB images from an unlabeled monocular video stream obtained by a monocular camera, feeding the RGB images into a depth estimation/refinement module, outputting depth maps, feeding the depth maps and the RGB images to a pose estimation/refinement module, the depths maps and the RGB images collectively defining pseudo RGB-D images, outputting camera poses and point clouds, and constructing a 3D map of a surrounding environment displayed on a visualization device.

公开(公告)号：US11468585B2

公开(公告)日：2022-10-11

申请号：US16987705

申请日：2020-08-07

Applicant: NEC Laboratories America, Inc.

Inventor： Quoc-Huy Tran ,  Pan Ji ,  Manmohan Chandraker ,  Lokender Tiwari

IPC: G06T7/579 ,  G06N3/08 ,  G06T15/10 ,  G06T7/20 ,  G06T7/80 ,  G06T15/00

Abstract: A method for improving geometry-based monocular structure from motion (SfM) by exploiting depth maps predicted by convolutional neural networks (CNNs) is presented. The method includes capturing a sequence of RGB images from an unlabeled monocular video stream obtained by a monocular camera, feeding the RGB images into a depth estimation/refinement module, outputting depth maps, feeding the depth maps and the RGB images to a pose estimation/refinement module, the depths maps and the RGB images collectively defining pseudo RGB-D images, outputting camera poses and point clouds, and constructing a 3D map of a surrounding environment displayed on a visualization device.