Events/ Workshop on Multiview Relationships in 3D Data 2017

October 29th, 2017
Venice, Italy
July 24th, 2017
Visit MVR3D 2017 website


The Multiview Relationships in 3D Data (MVR3D) workshop will be held in Venice on 29th October 2017, in conjunction with ICCV 2017.

The recent improvements in the 3D sensing technologies have caused a remarkable amplification in the utilization of 3D data. Common flexible representations governing the data in many applications are point clouds. Therefore, researchers are now taking on the challenge of accurately autostitching tens of millions of unstructured/structured points that include symmetries, self-similarities and that do not admit scan-order constraints. MVR3D will be dedicated 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.

Important dates

All dates are in international date format, i.e. YYYY-MM-DD

2017-07-24: Paper submission
2017-08-18: Notification of acceptance
2017-08-23: Camera ready
2017-10-29: Workshop starts

Topics of interest

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:

  • Global point cloud alignment
  • Multiview registration using scene priors
  • Learning methods for multiview 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 dataset methods for ground truth acquisition


  • Alex Bronstein, Associate Professor, Tel-Aviv University
  • Andrew Fitzgibbon, Partner Scientist, Microsoft Research
  • Radu Horaud, Senior Research Scientist, INRIA
  • Vladlen Koltun, Principal Scientist, Intel
  • Andreas Nüchter, Professor, JMU Würtzburg
  • Luc Robert, Software Architect Fellow, Bentley
  • Konrad Schindler, Professor, ETH Zurich
  • Christopher Zach, Research Scientist, Toshiba Europe

Add new comment