Show simple item record

dc.contributor.author
Truong, Prune
dc.contributor.author
Danelljan, Martin
dc.contributor.author
Van Gool, Luc
dc.contributor.author
Timofte, Radu
dc.contributor.editor
Larochelle, Hugo
dc.contributor.editor
Ranzato, Marc'Aurelio
dc.contributor.editor
Hadsell, Raia
dc.contributor.editor
Balcan, Maria F.
dc.contributor.editor
Lin, H.
dc.date.accessioned
2021-07-21T09:07:06Z
dc.date.available
2020-12-09T14:53:57Z
dc.date.available
2020-12-10T07:27:21Z
dc.date.available
2021-03-15T09:50:39Z
dc.date.available
2021-03-15T09:53:13Z
dc.date.available
2021-07-21T09:07:06Z
dc.date.issued
2021
dc.identifier.isbn
978-1-7138-2954-6
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/455564
dc.identifier.doi
10.3929/ethz-b-000455564
dc.description.abstract
The feature correlation layer serves as a key neural network module in numerous computer vision problems that involve dense correspondences between image pairs. It predicts a correspondence volume by evaluating dense scalar products between feature vectors extracted from pairs of locations in two images. However, this point-to-point feature comparison is insufficient when disambiguating multiple similar regions in an image, severely affecting the performance of the end task. We propose GOCor, a fully differentiable dense matching module, acting as a direct replacement to the feature correlation layer. The correspondence volume generated by our module is the result of an internal optimization procedure that explicitly accounts for similar regions in the scene. Moreover, our approach is capable of effectively learning spatial matching priors to resolve further matching ambiguities. We analyze our GOCor module in extensive ablative experiments. When integrated into state-of-the-art networks, our approach significantly outperforms the feature correlation layer for the tasks of geometric matching, optical flow, and dense semantic matching. The code and trained models will be made available at github.com/PruneTruong/GOCor
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
Curran
en_US
dc.rights.uri
http://rightsstatements.org/page/InC-NC/1.0/
dc.subject
computer vision
en_US
dc.subject
machine learning
en_US
dc.title
GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network
en_US
dc.type
Conference Paper
dc.rights.license
In Copyright - Non-Commercial Use Permitted
dc.date.published
2020
ethz.book.title
Advances in Neural Information Processing Systems 33
en_US
ethz.pages.start
14278
en_US
ethz.pages.end
14290
en_US
ethz.size
34 p. accepted version
en_US
ethz.version.deposit
publishedVersion
en_US
ethz.event
34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020)
en_US
ethz.event.location
Online
en_US
ethz.event.date
December 6-12, 2020
en_US
ethz.notes
Poster presentation held on December 8, 2020. Due to the Coronavirus (COVID-19) the conference was conducted virtually.
en_US
ethz.publication.place
Red Hook, NY
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.identifier.url
https://proceedings.neurips.cc/paper/2020/hash/a4a8a31750a23de2da88ef6a491dfd5c-Abstract.html
ethz.date.deposited
2020-12-09T14:54:08Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2021-03-15T09:50:50Z
ethz.rosetta.lastUpdated
2022-03-29T10:34:18Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=GOCor:%20Bringing%20Globally%20Optimized%20Correspondence%20Volumes%20into%20Your%20Neural%20Network&rft.date=2021&rft.spage=14278&rft.epage=14290&rft.au=Truong,%20Prune&Danelljan,%20Martin&Van%20Gool,%20Luc&Timofte,%20Radu&rft.isbn=978-1-7138-2954-6&rft.genre=proceeding&rft.btitle=Advances%20in%20Neural%20Information%20Processing%20Systems%2033
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record