DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Evaluation of CNN-based Single-Image Depth Estimation Methods

Koch, Tobias and Liebel, Lukas and Fraundorfer, Friedrich and Körner, Marco (2018) Evaluation of CNN-based Single-Image Depth Estimation Methods. In: Computer Vision - ECCV 2018 Workshops, pp. 331-348. European Conference on Computer Vision (ECCV) 2018, 08.-14. Sep. 2018, Munich, Germany. DOI: 10.1007/978-3-030-11015-4_25 ISBN 978-3-030-11014-7

[img] PDF

Official URL: https://eccv2018.org/


While an increasing interest in deep models for single-image depth estimation (SIDE) can be observed, established schemes for their evaluation are still limited. We propose a set of novel quality criteria, allowing for a more detailed analysis by focusing on specific characteristics of depth maps. In particular, we address the preservation of edges and planar regions, depth consistency, and absolute distance accuracy. In order to employ these metrics to evaluate and compare state-of-the-art SIDE approaches, we provide a new high-quality RGB-D dataset. We used a digital single-lens reflex (DSLR) camera together with a laser scanner to acquire high-resolution images and highly accurate depth maps. Experimental results show the validity of our proposed evaluation protocol.

Item URL in elib:https://elib.dlr.de/126833/
Document Type:Conference or Workshop Item (Speech)
Title:Evaluation of CNN-based Single-Image Depth Estimation Methods
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Koch, Tobiastobias.koch (at) tum.deUNSPECIFIED
Fraundorfer, Friedrichfriedrich.fraundorfer (at) dlr.deUNSPECIFIED
Körner, Marcomarco.koerner (at) tum.deUNSPECIFIED
Journal or Publication Title:Computer Vision - ECCV 2018 Workshops
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:No
DOI :10.1007/978-3-030-11015-4_25
Page Range:pp. 331-348
Series Name:Lecture Notes in Computer Science
Keywords:Single-image depth estimation Deep learning CNN RGB-D Benchmark Evaluation Dataset Error metrics
Event Title:European Conference on Computer Vision (ECCV) 2018
Event Location:Munich, Germany
Event Type:international Conference
Event Dates:08.-14. Sep. 2018
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Erdbeobachtung
DLR - Research theme (Project):R - Vorhaben hochauflösende Fernerkundungsverfahren
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By: Haschberger, Dr.-Ing. Peter
Deposited On:15 Mar 2019 13:17
Last Modified:31 Jul 2019 20:24

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.