Show simple item record

dc.contributor.author
Kaya, Berk
dc.contributor.author
Kumar, Suryansh
dc.contributor.author
Porto de Oliveira, Carlos Eduardo
dc.contributor.author
Ferrari, Vittorio
dc.contributor.author
Van Gool, Luc
dc.date.accessioned
2023-04-03T06:57:28Z
dc.date.available
2023-01-08T20:46:14Z
dc.date.available
2023-01-09T13:47:13Z
dc.date.available
2023-04-03T06:57:28Z
dc.date.issued
2023
dc.identifier.isbn
978-1-6654-9346-8
en_US
dc.identifier.isbn
978-1-6654-9347-5
en_US
dc.identifier.other
10.1109/WACV56688.2023.00314
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/590876
dc.identifier.doi
10.3929/ethz-b-000590876
dc.description.abstract
Multi-view photometric stereo (MVPS) is a preferred method for detailed and precise 3D acquisition of an object from images. Although popular methods for MVPS can provide outstanding results, they are often complex to execute and limited to isotropic material objects. To address such limitations, we present a simple, practical ap proach to MVPS, which works well for isotropic as well as other object material types such as anisotropic and glossy. The proposed approach in this paper exploits the benefit of uncertainty modeling in a deep neural network for a reliable fusion of photometric stereo (PS) and multi-view stereo (MVS) network predictions. Yet, contrary to the recently proposed state-of-the-art, we introduce neural volume rendering methodology for a trustworthy fusion of MVS and PS measurements. The advantage of introducing neural volume rendering is that it helps in the reliable modeling of objects with diverse material types, where existing MVS methods, PS methods, or both may fail. Furthermore, it allows us to work on neural 3D shape representation, which has recently shown outstanding results for many geometric processing tasks. Our suggested new loss function aims to fit the zero level set of the implicit neural function using the most certain MVS and PS network predictions coupled with weighted neural volume rendering cost. The proposed approach shows state-of-the-art results when tested extensively on several benchmark datasets.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.rights.uri
http://rightsstatements.org/page/InC-NC/1.0/
dc.subject
Algorithms: Low-level and physics-based vision
en_US
dc.subject
3D computer vision
en_US
dc.title
Multi-View Photometric Stereo Revisited
en_US
dc.type
Conference Paper
dc.rights.license
In Copyright - Non-Commercial Use Permitted
dc.date.published
2023-02-06
ethz.book.title
2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
en_US
ethz.pages.start
3125
en_US
ethz.pages.end
3134
en_US
ethz.version.deposit
acceptedVersion
en_US
ethz.event
23rd IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023)
en_US
ethz.event.location
Waikoloa, HI, USA
en_US
ethz.event.date
January 3-7, 2023
en_US
ethz.notes
Conference lecture held on January 6, 2023.
en_US
ethz.identifier.wos
ethz.publication.place
Piscataway, NJ
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02652 - Institut für Bildverarbeitung / Computer Vision Laboratory::03514 - Van Gool, Luc / Van Gool, Luc
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02652 - Institut für Bildverarbeitung / Computer Vision Laboratory::03514 - Van Gool, Luc / Van Gool, Luc
en_US
ethz.date.deposited
2023-01-08T20:46:14Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2023-04-03T06:57:29Z
ethz.rosetta.lastUpdated
2024-02-02T21:28:30Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Multi-View%20Photometric%20Stereo%20Revisited&rft.date=2023&rft.spage=3125&rft.epage=3134&rft.au=Kaya,%20Berk&Kumar,%20Suryansh&Porto%20de%20Oliveira,%20Carlos%20Eduardo&Ferrari,%20Vittorio&Van%20Gool,%20Luc&rft.isbn=978-1-6654-9346-8&978-1-6654-9347-5&rft.genre=proceeding&rft_id=info:doi/10.1109/WACV56688.2023.00314&rft.btitle=2023%20IEEE/CVF%20Winter%20Conference%20on%20Applications%20of%20Computer%20Vision%20(WACV)
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record