SYSTEMS AND METHODS FOR RECONSTRUCTION OF DENSE DEPTH MAPS

Title:

SYSTEMS AND METHODS FOR RECONSTRUCTION OF DENSE DEPTH MAPS

Document Type and Number:

WIPO Patent Application WO/2022/158890

Kind Code:

A1

Abstract:

A method by an extended reality (XR) display device includes obtaining image data and sparse depth points corresponding to a plurality of image frames to be displayed on one or more displays of the XR display device. The method further includes determining a plurality of sets of feature points for a current image frame of the plurality of image frames, constructing a cost function configured to propagate the sparse depth points corresponding to the current image frame based on the plurality of sets of feature points, and generating a dense depth map corresponding to the current image frame based on an evaluation of the cost function. The method thus includes rendering the current image frame on the one or more displays of the XR display device based on the dense depth map.

More Like This:

JP6735339	Systems and methods for video inspection of pantographs along fictitious contact lines
JP2023147276	DATA PROCESSING METHOD AND APPARATUS FOR TRAINING DEPTH INFORMATION ESTIMATION MODEL
WO/2019/082474	THREE-DIMENSIONAL INTRUSION DETECTION SYSTEM AND THREE-DIMENSIONAL INTRUSION DETECTION METHOD

Inventors:

XIONG YINGEN (US)
PERI CHRISTOPHER A (US)

Application Number:

PCT/KR2022/001084

Publication Date:

July 28, 2022

Filing Date:

January 21, 2022

Export Citation:

Click for automatic bibliography generation Help

Assignee:

SAMSUNG ELECTRONICS CO LTD (KR)

International Classes:

G06T7/593; G02B27/01; G06T7/13; G06T15/10; G06T19/00

Foreign References:

US20210004979A1	2021-01-07
JP2020061187A	2020-04-16

Other References:

FANGCHANG MA; SERTAC KARAMAN: "Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 21 September 2017 (2017-09-21), 201 Olin Library Cornell University Ithaca, NY 14853 , XP080822546
IM SUNG-HOON; CHOE GYEONGMIN; JEON HAE-GON; KWEON IN SO: "Depth from accidental motion using geometry prior", 2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), IEEE, 27 September 2015 (2015-09-27), pages 4160 - 4164, XP032827258, DOI: 10.1109/ICIP.2015.7351589
HUYNH LAM; NGUYEN PHONG; MATAS JIRI; RAHTU ESA; HEIKKILA JANNE: "Boosting Monocular Depth Estimation with Lightweight 3D Point Fusion", 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), IEEE, 10 October 2021 (2021-10-10), pages 12747 - 12756, XP034093050, DOI: 10.1109/ICCV48922.2021.01253

Attorney, Agent or Firm:

Y.P.LEE, MOCK & PARTNERS (KR)

Download PDF:

View/Download PDF PDF Help

Previous Patent: METHODS FOR PURIFYING AN ANTI-4-1BB/ANTI-HER2 BISPECIFIC ANTIBODY

Next Patent: CANCER-SPECIFIC TRANS-SPLICING RIBOZYME EXPRESSING IMMUNE CHECKPOINT INHIBITOR, AND USE THEREOR