An Efficient Deep Unrolling Super-Resolution Network for Lidar Automotive Scenes

Considering the high cost of high-resolution Lidar sensors, in this work, a novel Lidar super-resolution method is proposed to improve the performance on numerous autonomous vehicle perception tasks, including that of a Lidar odometer. Specifically, we propose a regularized optimization problem empl...

Full description

Saved in:
Bibliographic Details
Published in:2023 IEEE International Conference on Image Processing (ICIP) pp. 1840 - 1844
Main Authors: Gkillas, Alexandros, Lalos, Aris S., Ampeliotis, Dimitris
Format: Conference Proceeding
Language:English
Published: IEEE 08-10-2023
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Considering the high cost of high-resolution Lidar sensors, in this work, a novel Lidar super-resolution method is proposed to improve the performance on numerous autonomous vehicle perception tasks, including that of a Lidar odometer. Specifically, we propose a regularized optimization problem employing a learnable regularizer (neural network) to capture the properties of the data. To efficiently solve this problem, a deep unrolling methodology is proposed, thus forming an interpretable and well-justified deep architecture. Extensive experiments on a real-world lidar odometry application highlight that the proposed model exhibits both superior performance as well as a significantly reduced number of trainable parameters i.e., 99.75% less parameters, as compared to other deep learning methods. The source code used for this work can be found at our repository: repository.
AbstractList Considering the high cost of high-resolution Lidar sensors, in this work, a novel Lidar super-resolution method is proposed to improve the performance on numerous autonomous vehicle perception tasks, including that of a Lidar odometer. Specifically, we propose a regularized optimization problem employing a learnable regularizer (neural network) to capture the properties of the data. To efficiently solve this problem, a deep unrolling methodology is proposed, thus forming an interpretable and well-justified deep architecture. Extensive experiments on a real-world lidar odometry application highlight that the proposed model exhibits both superior performance as well as a significantly reduced number of trainable parameters i.e., 99.75% less parameters, as compared to other deep learning methods. The source code used for this work can be found at our repository: repository.
Author Lalos, Aris S.
Ampeliotis, Dimitris
Gkillas, Alexandros
Author_xml – sequence: 1
  givenname: Alexandros
  surname: Gkillas
  fullname: Gkillas, Alexandros
  organization: Athena Research Center,Industrial Systems Institute,Greece
– sequence: 2
  givenname: Aris S.
  surname: Lalos
  fullname: Lalos, Aris S.
  organization: Athena Research Center,Industrial Systems Institute,Greece
– sequence: 3
  givenname: Dimitris
  surname: Ampeliotis
  fullname: Ampeliotis, Dimitris
  organization: Athena Research Center,Industrial Systems Institute,Greece
BookMark eNo1j8FKxDAURSPowhn9A8H8QGtf0rTJstRRC0UHx1kPafoiwU5S0lbx7x1QV3dx4HDuipz74JGQW8hSgEzdNXWzzRUXKmUZ4ylkjDEpijOygpJJUJKL4pJsK0831jrj0M_0HnGkex_DMDj_TnfLiDF5xSkMy-yCp884f4X4QW2ItHW9jrRa5nAMs_tEujPocboiF1YPE17_7ZrsHzZv9VPSvjw2ddUmjgk-J3nen2J4qVkpFJeAkBUctOwKoxlqaSQaCwAmt0bwvLdGFbIT_YkI1VnB1-Tm1-sQ8TBGd9Tx-_D_kv8ADPJNUA
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ICIP49359.2023.10222856
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library Online
  url: http://ieeexplore.ieee.org/Xplore/DynWel.jsp
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 1728198356
9781728198354
EndPage 1844
ExternalDocumentID 10222856
Genre orig-research
GroupedDBID 6IE
6IH
CBEJK
RIE
RIO
ID FETCH-LOGICAL-i253t-44d85637a2759381e10631a8b6ca2ea8c8ecf111c4fc534dfc968b5da8c59bf53
IEDL.DBID RIE
IngestDate Wed Jan 10 09:27:48 EST 2024
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i253t-44d85637a2759381e10631a8b6ca2ea8c8ecf111c4fc534dfc968b5da8c59bf53
OpenAccessLink https://doi.org/10.1109/icip49359.2023.10222856
PageCount 5
ParticipantIDs ieee_primary_10222856
PublicationCentury 2000
PublicationDate 2023-Oct.-8
PublicationDateYYYYMMDD 2023-10-08
PublicationDate_xml – month: 10
  year: 2023
  text: 2023-Oct.-8
  day: 08
PublicationDecade 2020
PublicationTitle 2023 IEEE International Conference on Image Processing (ICIP)
PublicationTitleAbbrev ICIP
PublicationYear 2023
Publisher IEEE
Publisher_xml – name: IEEE
Score 2.29969
Snippet Considering the high cost of high-resolution Lidar sensors, in this work, a novel Lidar super-resolution method is proposed to improve the performance on...
SourceID ieee
SourceType Publisher
StartPage 1840
SubjectTerms Deep learning
deep unrolling
Laser radar
lidar
lidar odometry
Neural networks
Odometers
Sensors
SLAM
Source coding
super-resolution
Superresolution
Title An Efficient Deep Unrolling Super-Resolution Network for Lidar Automotive Scenes
URI https://ieeexplore.ieee.org/document/10222856
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://sdu.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LawMhEJamp57a0pS-8dCreayrjseQBwmUEEgDvQUfs5DLJmyz_f1VN0npoYfexAfKqDM-vvmGkFftHBTcGCYKsCzPBWegvWQybHLgYLVNJEnTpZp_wGgcaXLYyRcGERP4DDsxmf7y_dbV8amsm24nIGSLtJSGxlnrgNnq93R3Npwt8uhp2okxwTvH2r_ipiSzMbn8Z4dXpP3jgEcXJ9NyTc6wvCGLQUnHifEhNKIjxB1dlVVDqk2X9Q4rFh_jm6VE5w2-m4ZDKX3beFPRQb1P0LsvpEsXVVybrCbj9-GUHQIisE0m-D6I0ofBcGUyJXQwtRjuc7xvwEpnMjTgAF0RlJfLCyd47gunJVjhQ4nQthD8lpyX2xLvCJU8KDZQ4HOw4UQljRboVE9lhfIyd3hP2lEc613DebE-SuLhj_xHchGF3qDjnsj5vqrxmbQ-ff2SpukbLdqVTw
link.rule.ids 310,311,782,786,791,792,798,27934,54767
linkProvider IEEE
linkToHtml http://sdu.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JTwIxFG4ED3pSI8bdHryWZbofCUsgIiEBEm-k075JuAxkZPz9th3AePDgremSNq_te12-9z2EXrW1KqPGEJ6plDDGKVHaCSL8JldUpTqNJEmjuZx-qP4g0OSQoy8MAETwGTRDMv7lu40tw1NZK95OFBc1dMqZFLJy19qjtjpt3Rr3xjMWfE2bISp481D_V-SUaDiGF__s8hI1flzw8OxoXK7QCeTXaNbN8SByPvhGuA-wxcu8qGi18bzcQkHCc3y1mPC0QnhjfyzFk7UzBe6Wuwi--wI8t0HJNdByOFj0RmQfEoGsE053XpjOD4ZKk0iuvbEFf6OjHaNSYU0CRlkFNvPqy7LMcspcZrVQKXe-hOs04_QG1fNNDrcIC-pVm5LKMZX6M5UwmoOVbZlk0glm4Q41gjhW24r1YnWQxP0f-S_obLR4n6wm4-nbAzoPE1Bh5R5RfVeU8IRqn658jlP2DTq9mKA
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2023+IEEE+International+Conference+on+Image+Processing+%28ICIP%29&rft.atitle=An+Efficient+Deep+Unrolling+Super-Resolution+Network+for+Lidar+Automotive+Scenes&rft.au=Gkillas%2C+Alexandros&rft.au=Lalos%2C+Aris+S.&rft.au=Ampeliotis%2C+Dimitris&rft.date=2023-10-08&rft.pub=IEEE&rft.spage=1840&rft.epage=1844&rft_id=info:doi/10.1109%2FICIP49359.2023.10222856&rft.externalDocID=10222856