ToFNest: Efficient normal estimation for time-of-flight depth cameras

In this work, we propose an efficient normal estimation method for depth images acquired by Time-of-Flight (ToF) cameras based on feature pyramid networks (FPN). We perform the normal estimation starting from the 2D depth images, projecting the measured data into the 3D space and computing the loss...

Full description

Saved in:
Bibliographic Details
Main Authors: Molnar, Szilard, Kelenyi, Benjamin, Tamas, Levente
Format: Conference Proceeding
Language:English
Subjects:
Cameras
Codes
Computer vision
Conferences
Estimation
Runtime
Three-dimensional displays
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 1798
container_issue
container_start_page 1791
container_title
container_volume
creator Molnar, Szilard
Kelenyi, Benjamin
Tamas, Levente
description In this work, we propose an efficient normal estimation method for depth images acquired by Time-of-Flight (ToF) cameras based on feature pyramid networks (FPN). We perform the normal estimation starting from the 2D depth images, projecting the measured data into the 3D space and computing the loss function for the point cloud normal. Despite its simplicity, our method called ToFNest proves to be efficient in terms of robustness and runtime. In order to validate ToFNest we performed extensive evaluations using both public and custom outdoor datasets. Compared with the state of the art methods, our algorithm is faster by an order of magnitude without losing precision on public datasets. The demo code is available on https://github.com/molnarszilard/ToFNest
doi_str_mv 10.1109/ICCVW54120.2021.00205
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_9607779</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9607779</ieee_id><sourcerecordid>9607779</sourcerecordid><originalsourceid>FETCH-LOGICAL-i133t-583a14e155138e5d2d36d609b7a0e3b96394a3f9395a18cdd5986f8f5be3cb423</originalsourceid><addsrcrecordid>eNotjsFKw0AURUdBsNR-gQjzA6nvzZuZ5LmT0Gqh6KbqskySN3akSUqSjX9vwa4u5ywOV6kHhCUi8OOmLD-_nEUDSwMGlwAG3JVacF6g984CMtK1mhmbU8Zs7a1ajOMPAKBHxwQztdr16zcZpye9ijHVSbpJd_3QhqM-29SGKfWdjv2gzyBZH7N4TN-HSTdymg66Dq0MYbxTNzEcR1lcdq4-1qtd-Zpt31825fM2S0g0Za6ggFbQOaRCXGMa8o0HrvIAQhV7YhsoMrELWNRN47jwsYiuEqora2iu7v-7SUT2p-H8b_jds4c8z5n-ANUaTE4</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>ToFNest: Efficient normal estimation for time-of-flight depth cameras</title><source>IEEE Xplore All Conference Series</source><creator>Molnar, Szilard ; Kelenyi, Benjamin ; Tamas, Levente</creator><creatorcontrib>Molnar, Szilard ; Kelenyi, Benjamin ; Tamas, Levente</creatorcontrib><description>In this work, we propose an efficient normal estimation method for depth images acquired by Time-of-Flight (ToF) cameras based on feature pyramid networks (FPN). We perform the normal estimation starting from the 2D depth images, projecting the measured data into the 3D space and computing the loss function for the point cloud normal. Despite its simplicity, our method called ToFNest proves to be efficient in terms of robustness and runtime. In order to validate ToFNest we performed extensive evaluations using both public and custom outdoor datasets. Compared with the state of the art methods, our algorithm is faster by an order of magnitude without losing precision on public datasets. The demo code is available on https://github.com/molnarszilard/ToFNest</description><identifier>EISSN: 2473-9944</identifier><identifier>EISBN: 9781665401913</identifier><identifier>EISBN: 1665401915</identifier><identifier>DOI: 10.1109/ICCVW54120.2021.00205</identifier><identifier>CODEN: IEEPAD</identifier><language>eng</language><publisher>IEEE</publisher><subject>Cameras ; Codes ; Computer vision ; Conferences ; Estimation ; Runtime ; Three-dimensional displays</subject><ispartof>2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021, p.1791-1798</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9607779$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9607779$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Molnar, Szilard</creatorcontrib><creatorcontrib>Kelenyi, Benjamin</creatorcontrib><creatorcontrib>Tamas, Levente</creatorcontrib><title>ToFNest: Efficient normal estimation for time-of-flight depth cameras</title><title>2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)</title><addtitle>ICCVW</addtitle><description>In this work, we propose an efficient normal estimation method for depth images acquired by Time-of-Flight (ToF) cameras based on feature pyramid networks (FPN). We perform the normal estimation starting from the 2D depth images, projecting the measured data into the 3D space and computing the loss function for the point cloud normal. Despite its simplicity, our method called ToFNest proves to be efficient in terms of robustness and runtime. In order to validate ToFNest we performed extensive evaluations using both public and custom outdoor datasets. Compared with the state of the art methods, our algorithm is faster by an order of magnitude without losing precision on public datasets. The demo code is available on https://github.com/molnarszilard/ToFNest</description><subject>Cameras</subject><subject>Codes</subject><subject>Computer vision</subject><subject>Conferences</subject><subject>Estimation</subject><subject>Runtime</subject><subject>Three-dimensional displays</subject><issn>2473-9944</issn><isbn>9781665401913</isbn><isbn>1665401915</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2021</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotjsFKw0AURUdBsNR-gQjzA6nvzZuZ5LmT0Gqh6KbqskySN3akSUqSjX9vwa4u5ywOV6kHhCUi8OOmLD-_nEUDSwMGlwAG3JVacF6g984CMtK1mhmbU8Zs7a1ajOMPAKBHxwQztdr16zcZpye9ijHVSbpJd_3QhqM-29SGKfWdjv2gzyBZH7N4TN-HSTdymg66Dq0MYbxTNzEcR1lcdq4-1qtd-Zpt31825fM2S0g0Za6ggFbQOaRCXGMa8o0HrvIAQhV7YhsoMrELWNRN47jwsYiuEqora2iu7v-7SUT2p-H8b_jds4c8z5n-ANUaTE4</recordid><startdate>202110</startdate><enddate>202110</enddate><creator>Molnar, Szilard</creator><creator>Kelenyi, Benjamin</creator><creator>Tamas, Levente</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>202110</creationdate><title>ToFNest: Efficient normal estimation for time-of-flight depth cameras</title><author>Molnar, Szilard ; Kelenyi, Benjamin ; Tamas, Levente</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i133t-583a14e155138e5d2d36d609b7a0e3b96394a3f9395a18cdd5986f8f5be3cb423</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Cameras</topic><topic>Codes</topic><topic>Computer vision</topic><topic>Conferences</topic><topic>Estimation</topic><topic>Runtime</topic><topic>Three-dimensional displays</topic><toplevel>online_resources</toplevel><creatorcontrib>Molnar, Szilard</creatorcontrib><creatorcontrib>Kelenyi, Benjamin</creatorcontrib><creatorcontrib>Tamas, Levente</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library Online</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Molnar, Szilard</au><au>Kelenyi, Benjamin</au><au>Tamas, Levente</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>ToFNest: Efficient normal estimation for time-of-flight depth cameras</atitle><btitle>2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)</btitle><stitle>ICCVW</stitle><date>2021-10</date><risdate>2021</risdate><spage>1791</spage><epage>1798</epage><pages>1791-1798</pages><eissn>2473-9944</eissn><eisbn>9781665401913</eisbn><eisbn>1665401915</eisbn><coden>IEEPAD</coden><abstract>In this work, we propose an efficient normal estimation method for depth images acquired by Time-of-Flight (ToF) cameras based on feature pyramid networks (FPN). We perform the normal estimation starting from the 2D depth images, projecting the measured data into the 3D space and computing the loss function for the point cloud normal. Despite its simplicity, our method called ToFNest proves to be efficient in terms of robustness and runtime. In order to validate ToFNest we performed extensive evaluations using both public and custom outdoor datasets. Compared with the state of the art methods, our algorithm is faster by an order of magnitude without losing precision on public datasets. The demo code is available on https://github.com/molnarszilard/ToFNest</abstract><pub>IEEE</pub><doi>10.1109/ICCVW54120.2021.00205</doi><tpages>8</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2473-9944
ispartof 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021, p.1791-1798
issn 2473-9944
language eng
recordid cdi_ieee_primary_9607779
source IEEE Xplore All Conference Series
subjects Cameras
Codes
Computer vision
Conferences
Estimation
Runtime
Three-dimensional displays
title ToFNest: Efficient normal estimation for time-of-flight depth cameras
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-19T16%3A56%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=ToFNest:%20Efficient%20normal%20estimation%20for%20time-of-flight%20depth%20cameras&rft.btitle=2021%20IEEE/CVF%20International%20Conference%20on%20Computer%20Vision%20Workshops%20(ICCVW)&rft.au=Molnar,%20Szilard&rft.date=2021-10&rft.spage=1791&rft.epage=1798&rft.pages=1791-1798&rft.eissn=2473-9944&rft.coden=IEEPAD&rft_id=info:doi/10.1109/ICCVW54120.2021.00205&rft.eisbn=9781665401913&rft.eisbn_list=1665401915&rft_dat=%3Cieee_CHZPO%3E9607779%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i133t-583a14e155138e5d2d36d609b7a0e3b96394a3f9395a18cdd5986f8f5be3cb423%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=9607779&rfr_iscdi=true