Zur Kurzanzeige

dc.contributor.author
Li, Zuoyue
dc.contributor.author
Li, Zhenqiang
dc.contributor.author
Cui, Zhaopeng
dc.contributor.author
Qin, Rongjun
dc.contributor.author
Pollefeys, Marc
dc.contributor.author
Oswald, Martin R.
dc.date.accessioned
2022-06-30T11:53:41Z
dc.date.available
2021-11-25T13:08:43Z
dc.date.available
2021-12-02T13:38:15Z
dc.date.available
2022-06-21T09:38:05Z
dc.date.available
2022-06-30T11:53:41Z
dc.date.issued
2021
dc.identifier.isbn
978-1-6654-2812-5
en_US
dc.identifier.other
10.1109/ICCV48922.2021.01221
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/516883
dc.description.abstract
We present a novel method for synthesizing both temporally and geometrically consistent street-view panoramic video from a single satellite image and camera trajectory. Existing cross-view synthesis approaches focus on images, while video synthesis in such a case has not yet received enough attention. For geometrical and temporal consistency, our approach explicitly creates a 3D point cloud representation of the scene and maintains dense 3D-2D correspondences across frames that reflect the geometric scene configuration inferred from the satellite view. As for synthesis in the 3D space, we implement a cascaded network architecture with two hourglass modules to generate point-wise coarse and fine features from semantics and per-class latent vectors, followed by projection to frames and an upsampling module to obtain the final realistic video. By leveraging computed correspondences, the produced street-view video frames adhere to the 3D geometric scene structure and maintain temporal consistency. Qualitative and quantitative experiments demonstrate superior results compared to other state-of-the-art synthesis approaches that either lack temporal consistency or realistic appearance. To the best of our knowledge, our work is the first one to synthesize cross-view images to videos.
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.title
Sat2Vid: Street-View Panoramic Video Synthesis From a Single Satellite Image
en_US
dc.type
Conference Paper
dc.date.published
2021-02-28
ethz.book.title
2021 IEEE/CVF International Conference on Computer Vision (ICCV)
en_US
ethz.pages.start
12436
en_US
ethz.pages.end
12445
en_US
ethz.event
18th International Conference on Computer Vision (ICCV 2021)
en_US
ethz.event.location
Online
ethz.event.date
October 11-17, 2021
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::02150 - Dep. Informatik / Dep. of Computer Science::02659 - Institut für Visual Computing / Institute for Visual Computing::03766 - Pollefeys, Marc / Pollefeys, Marc
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02659 - Institut für Visual Computing / Institute for Visual Computing::03766 - Pollefeys, Marc / Pollefeys, Marc
en_US
ethz.date.deposited
2021-11-25T13:08:49Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2022-06-21T09:38:12Z
ethz.rosetta.lastUpdated
2023-02-07T03:54:49Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Sat2Vid:%20Street-View%20Panoramic%20Video%20Synthesis%20From%20a%20Single%20Satellite%20Image&rft.date=2021&rft.spage=12436&rft.epage=12445&rft.au=Li,%20Zuoyue&Li,%20Zhenqiang&Cui,%20Zhaopeng&Qin,%20Rongjun&Pollefeys,%20Marc&rft.isbn=978-1-6654-2812-5&rft.genre=proceeding&rft_id=info:doi/10.1109/ICCV48922.2021.01221&rft.btitle=2021%20IEEE/CVF%20International%20Conference%20on%20Computer%20Vision%20(ICCV)
 Printexemplar via ETH-Bibliothek suchen

Dateien zu diesem Eintrag

DateienGrößeFormatIm Viewer öffnen

Zu diesem Eintrag gibt es keine Dateien.

Publikationstyp

Zur Kurzanzeige