Deep Soft Procrustes for Markerless Volumetric Sensor Alignment
With the advent of consumer grade depth sensors, low-cost volumetric capture systems are easier to deploy. Their wider adoption though depends on their usability and by extension on the practicality of spatially aligning multiple sensors. Most existing alignment approaches employ visual patterns, e....
Saved in:
Main Authors | , , , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
23.03.2020
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | With the advent of consumer grade depth sensors, low-cost volumetric capture
systems are easier to deploy. Their wider adoption though depends on their
usability and by extension on the practicality of spatially aligning multiple
sensors. Most existing alignment approaches employ visual patterns, e.g.
checkerboards, or markers and require high user involvement and technical
knowledge. More user-friendly and easier-to-use approaches rely on markerless
methods that exploit geometric patterns of a physical structure. However,
current SoA approaches are bounded by restrictions in the placement and the
number of sensors. In this work, we improve markerless data-driven
correspondence estimation to achieve more robust and flexible multi-sensor
spatial alignment. In particular, we incorporate geometric constraints in an
end-to-end manner into a typical segmentation based model and bridge the
intermediate dense classification task with the targeted pose estimation one.
This is accomplished by a soft, differentiable procrustes analysis that
regularizes the segmentation and achieves higher extrinsic calibration
performance in expanded sensor placement configurations, while being
unrestricted by the number of sensors of the volumetric capture system. Our
model is experimentally shown to achieve similar results with marker-based
methods and outperform the markerless ones, while also being robust to the pose
variations of the calibration structure. Code and pretrained models are
available at https://vcl3d.github.io/StructureNet/. |
---|---|
AbstractList | With the advent of consumer grade depth sensors, low-cost volumetric capture
systems are easier to deploy. Their wider adoption though depends on their
usability and by extension on the practicality of spatially aligning multiple
sensors. Most existing alignment approaches employ visual patterns, e.g.
checkerboards, or markers and require high user involvement and technical
knowledge. More user-friendly and easier-to-use approaches rely on markerless
methods that exploit geometric patterns of a physical structure. However,
current SoA approaches are bounded by restrictions in the placement and the
number of sensors. In this work, we improve markerless data-driven
correspondence estimation to achieve more robust and flexible multi-sensor
spatial alignment. In particular, we incorporate geometric constraints in an
end-to-end manner into a typical segmentation based model and bridge the
intermediate dense classification task with the targeted pose estimation one.
This is accomplished by a soft, differentiable procrustes analysis that
regularizes the segmentation and achieves higher extrinsic calibration
performance in expanded sensor placement configurations, while being
unrestricted by the number of sensors of the volumetric capture system. Our
model is experimentally shown to achieve similar results with marker-based
methods and outperform the markerless ones, while also being robust to the pose
variations of the calibration structure. Code and pretrained models are
available at https://vcl3d.github.io/StructureNet/. |
Author | Daras, Petros Zarpalas, Dimitrios Sterzentsenko, Vladimiros Zioulis, Nikolaos Doumanoglou, Alexandros Thermos, Spyridon |
Author_xml | – sequence: 1 givenname: Vladimiros surname: Sterzentsenko fullname: Sterzentsenko, Vladimiros – sequence: 2 givenname: Alexandros surname: Doumanoglou fullname: Doumanoglou, Alexandros – sequence: 3 givenname: Spyridon surname: Thermos fullname: Thermos, Spyridon – sequence: 4 givenname: Nikolaos surname: Zioulis fullname: Zioulis, Nikolaos – sequence: 5 givenname: Dimitrios surname: Zarpalas fullname: Zarpalas, Dimitrios – sequence: 6 givenname: Petros surname: Daras fullname: Daras, Petros |
BackLink | https://doi.org/10.48550/arXiv.2003.10176$$DView paper in arXiv |
BookMark | eNotz81KxDAUhuEsdKGjF-DK3EBrfk7TZiXD-AsjCjO4LSfpqRTbZEg6onevjq6-xQsfPKfsKMRAjF1IUUJTVeIK0-fwUSohdCmFrM0Ju74h2vFN7Gf-kqJP-zxT5n1M_AnTO6WRcuavcdxPNKfB8w2F_BOX4_AWJgrzGTvuccx0_r8Ltr273a4eivXz_eNquS7Q1KYwSvkOLDXeOOuBEGpwHk1Vk6q8RUBvoDFaGOsk9KpDbZ0zQoCU0HSgF-zy7_YgaHdpmDB9tb-S9iDR33LRRRU |
ContentType | Journal Article |
Copyright | http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
Copyright_xml | – notice: http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
DBID | AKY GOX |
DOI | 10.48550/arxiv.2003.10176 |
DatabaseName | arXiv Computer Science arXiv.org |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: GOX name: arXiv.org url: http://arxiv.org/find sourceTypes: Open Access Repository |
DeliveryMethod | fulltext_linktorsrc |
ExternalDocumentID | 2003_10176 |
GroupedDBID | AKY GOX |
ID | FETCH-LOGICAL-a676-622cd49e8c6b9c4ea474bca657e25c9a4ac64863069b14f2da39bb60041148d43 |
IEDL.DBID | GOX |
IngestDate | Mon Jan 08 05:37:18 EST 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-a676-622cd49e8c6b9c4ea474bca657e25c9a4ac64863069b14f2da39bb60041148d43 |
OpenAccessLink | https://arxiv.org/abs/2003.10176 |
ParticipantIDs | arxiv_primary_2003_10176 |
PublicationCentury | 2000 |
PublicationDate | 2020-03-23 |
PublicationDateYYYYMMDD | 2020-03-23 |
PublicationDate_xml | – month: 03 year: 2020 text: 2020-03-23 day: 23 |
PublicationDecade | 2020 |
PublicationYear | 2020 |
Score | 1.7686357 |
SecondaryResourceType | preprint |
Snippet | With the advent of consumer grade depth sensors, low-cost volumetric capture
systems are easier to deploy. Their wider adoption though depends on their... |
SourceID | arxiv |
SourceType | Open Access Repository |
SubjectTerms | Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning |
Title | Deep Soft Procrustes for Markerless Volumetric Sensor Alignment |
URI | https://arxiv.org/abs/2003.10176 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwdV1LSwMxEB7anryIolKf5OB1cZvNJpuTFLUWQT20yt5KZjYrBZHSbcWf7yS7ohevmVwyYR4fM_MNwKWsnc1rNiRjPSXKG_aD6IoEtSODMqU87k95fNLTF_VQ5mUPxM8sjFt_LT9bfmBsrkLnVGQC0n3oSxlatu6fy7Y4Gam4uvu_9zjHjEd_gsRkD3a77E6M2-_Yh57_OIDrW-9XYsb-ToS2_DDk4BvByaIIgzI-VLsb8Rq9RKDLFzNGliwcvy_fYqn-EOaTu_nNNOn2FiROG51oKalS1hek0ZLyThmF5HRuvMzJOuVIq0Jzrm5xpGpZucwi6sB8xdikUtkRDBj6-yEINsbK1LqwNQUcVSBRjekIC8KKrUkewzC-drFqqSnCUslsERVx8r_oFHZkQI1plsjsDAab9dafc2jd4EXU7zeH8HlI |
link.rule.ids | 228,230,786,891 |
linkProvider | Cornell University |
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%3Ajournal&rft.genre=article&rft.atitle=Deep+Soft+Procrustes+for+Markerless+Volumetric+Sensor+Alignment&rft.au=Sterzentsenko%2C+Vladimiros&rft.au=Doumanoglou%2C+Alexandros&rft.au=Thermos%2C+Spyridon&rft.au=Zioulis%2C+Nikolaos&rft.date=2020-03-23&rft_id=info:doi/10.48550%2Farxiv.2003.10176&rft.externalDocID=2003_10176 |