[visionlist] MVR3D 2017: ICCV Workshop on Multiview Relationships in 3D Data - Call For Papers

Tolga Birdal tbirdal at gmail.com
Thu Jun 8 11:36:49 -04 2017


*CALL FOR PAPERS (CfP)*

ICCV International Workshop on Multiview Relationships in 3D Data (MVR3D)
29 October 2017
mvr3d.github.io
*We kindly apologize for multiple copies.*

*Venue & Contact*
*Venue*: Lungomare Guglielmo Marconi, 30, 30126 Lido di Venezia - Venice,
Italy
*E-mail*: multiview.workshop at gmail.com

*Important Dates*

Please find below our strict deadlines for paper submission and
notifications.


• Paper submission:  July 24, 2017
• Notification of acceptance:  August 18, 2017
• Camera ready:    August 23, 2017
• Workshop date:  October 29, 2017

*Awards *

Thanks to our supporters, our generous awards will include:


• Professional license for *3DF Zephyr *software, sponsored by 3D Flow,
granted to the best paper
• *Monetary prize(s)* for selected paper(s), sponsored by Siemens AG
• A *RealSense *camera, sponsored by Intel, granted to the best student
paper
• First authors of *all accepted papers *receive licenses for the light
version of *3DF Zephyr* software, sponsored by 3D Flow

*Focus*

The recent improvements in the 3D sensing technologies have caused a
remarkable amplification in the utilization of 3D data. 3D information has
found tremendous use in Autonomous Driving, 3D Mapping, Quality Control,
Drones and UAVs or Robot Guidance to name but a few applicative domains.
These applications typically fuse different modalities such as range
images, stereo triangulations, structure-from-motion reconstructions or
laser scans. A common flexible representation governing all these are point
clouds. Thus, in many of the applications that rely on multiple 3D
acquisitions, good registration of point clouds is a prerequisite. Yet,
when unstructured dense scans of large scenes are of concern, establishing
the alignment in a fully automatic manner is far from being trivial -- a
difficulty that is exacerbated when the scans in question are allowed to
undergo locally non-rigid deformations due to mis-calibration of the
capturing device or object movement.


In such a complex scenario, researchers are now taking on the challenge of
accurately auto-stitching tens of millions of unstructured/structured
points that include symmetries, self-similarities and that do not admit
scan-order constraints. This workshop will be dedicated to exploring the
theoretical and practical aspects of obtaining multi-view global alignment
and registration of scans captured by any 3D data modality. Our main
objective is to gather together industry experts, academic researchers, and
practitioners of 3D data acquisition and scene reconstruction into a lively
environment for discussing methodologies and challenges raised by the
emergence of large-scale 3D reconstruction applications; as a targeted
topic venue, this workshop will offer participants a unique opportunity to
network with a diverse but focused research community.

*Topics*
The goal of this workshop is to push the frontier in the area of global
multi-scan alignment. Focal points for discussions and solicited
submissions include but are not limited to:

   - *Multiview registration using scene priors*
   - *Global point cloud alignment*
   - *Learning methods for correspondence estimation*
   - *3D Object reconstruction from multiple views*
   - *Joint registration and segmentation of multiple scans*
   - *Joint matching of multiple non-rigid surfaces*
   - *Multiview object detection*
   - *Multi-object Instance reconstruction*
   - *Feature descriptors for multiview 3D matching*
   - *Multiview pose estimation*
   - *Joint processing of multiple point clouds*
   - *Pose averaging and error diffusion on graphs*
   - *Multiview stitching of 3D scans on mobile and embedded devices*
   - *Practical applications of multiple scan registration on large
   scale settings*
   - *Datasets and methods for ground truth acquisition*

*Invited Speakers*

Our invited speakers come from top research institutions and companies
around the globe, and are leading figures in the topics covered by the
workshop:


Andrew Fitzgibbon, Partner Scientist, Microsoft Research

Alex Bronstein, Associate Professor, Tel-Aviv University

Vladlen Koltun, Principal Scientist, Intel

Radu Horaud, Senior Research Scientist, INRIA

Andreas Nüchter, Professor for Telematics, Julius-Maximilians-University

Konrad Schindler, Professor, ETH Zurich

Chrisopher Zach, Research Scientist, Toshiba Europe

Luc Robert, Software Architect, Fellow, Bentley


*Submission *

We are looking forward to submissions, following the enlisted guidelines:

   - Submitted papers should not have been published, accepted or under
   review elsewhere.
   - The submissions can be up to 8 pages (excluding references).
   - All the papers must be submitted using the templates provided on our
   webpages.
   - All the submissions will be subject to double-blind review process.
   Therefore author names, affiliations, emails, personal acknowledgements,
   etc. should be removed from the paper.
   - Every accepted paper requires that at least one author has a
   workshop-inclusive ICCV registration
   <http://iccv2017.thecvf.com/attend/registration>.
   - Here are further detailed guidelines
   <http://iccv2017.thecvf.com/files/egpaper_for_review.pdf>.
   - Published papers will be included in ICCV 2017 proceedings.


*Workshop Chairs*
Here are the humble people behind MVR3D 2017:

*Tolga Birdal*, Technical University of Munich
*Emanuele Rodol**à*, Università della Svizzera Italiana
*Gul Varol*, INRIA
*Slobodan Ilic*, Siemens AG
*Umberto Castellani*, University of Verona
*Andrea Torsello*, Ca' Foscari University of Venice

Looking forward to meeting in Venice!

-- 

*On behalf of all MVR3D organizers,*
*Tolga Birdal*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20170608/9430787f/attachment-0001.html>


More information about the visionlist mailing list