loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Umashankar Deekshith ; Nishit Gajjar ; Max Schwarz and Sven Behnke

Affiliation: Autonomous Intelligent Systems Group of University of Bonn, Germany

Keyword(s): Dense Correspondence, Deep Learning, Pixel Descriptors.

Abstract: Correspondence estimation is one of the most widely researched and yet only partially solved area of computer vision with many applications in tracking, mapping, recognition of objects and environment. In this paper, we propose a novel way to estimate dense correspondence on an RGB image where visual descriptors are learned from video examples by training a fully convolutional network. Most deep learning methods solve this by training the network with a large set of expensive labeled data or perform labeling through strong 3D generative models using RGB-D videos. Our method learns from RGB videos using contrastive loss, where relative labeling is estimated from optical flow. We demonstrate the functionality in a quantitative analysis on rendered videos, where ground truth information is available. Not only does the method perform well on test data with the same background, it also generalizes to situations with a new background. The descriptors learned are unique and the representati ons determined by the network are global. We further show the applicability of the method to real-world videos. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.142.53.68

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Deekshith, U.; Gajjar, N.; Schwarz, M. and Behnke, S. (2020). Visual Descriptor Learning from Monocular Video. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP; ISBN 978-989-758-402-2; ISSN 2184-4321, SciTePress, pages 444-451. DOI: 10.5220/0008989304440451

@conference{visapp20,
author={Umashankar Deekshith. and Nishit Gajjar. and Max Schwarz. and Sven Behnke.},
title={Visual Descriptor Learning from Monocular Video},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP},
year={2020},
pages={444-451},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008989304440451},
isbn={978-989-758-402-2},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP
TI - Visual Descriptor Learning from Monocular Video
SN - 978-989-758-402-2
IS - 2184-4321
AU - Deekshith, U.
AU - Gajjar, N.
AU - Schwarz, M.
AU - Behnke, S.
PY - 2020
SP - 444
EP - 451
DO - 10.5220/0008989304440451
PB - SciTePress

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185 (National fixed network call)
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic