June 17, 2019, Long Beach, CA (USA)

in conjunction with CVPR 2019

About

Both photogrammetry and computer vision, refer to the science of acquiring information about the physical world from image data. During the recent decades both fields have matured and converged, which is best illustrated by the widespread usage of the term “Photogrammetric Computer Vision” (PCV). The PCV 2019 workshop aims at providing a forum for collaboration between the computer vision and photogrammetry communities to discuss modern challenges and ideas, propose new and contemporary benchmarks, elaborate on the overlap to machine learning, mathematics and other related areas, and boost the development in the highly challenging and quickly evolving field of photogrammetric computer vision.

Program

All accepted papers can be found here.

13:30-13:45 Welcome

13:45-14:30 Keynote: Dr. Christoph Strecha (Pix4D) - Industry insights for photogrammetry applications [Abstract]

14:30-15:10 Orals

Robustifying relative orientations with respect to repetitive structures and very short baselines for global SfM, Xin Wang (Leibniz Universität Hannover); Teng Xiao (Wuhan University); Christian Heipke (Leibniz Universität Hannover)

Measuring the Effects of Temporal Coherence in Depth Estimation for Dynamic Scenes, Iraklis Tsekourakis (Stevens Institute of Technology); Philippos Mordohai (Stevens Institute of Technology)

15:10-16:00 Coffee Break

16:00-16:45 Keynote: Prof. Daniel Cremers (Technical University of Munich) - Realtime Visual SLAM for Autonomous Systems [Abstract]

16:45-17:45 Orals

A Digital Image Processing Pipeline for Modelling of Realistic Noise in Synthetic Images, Ronny Hänsch (Technische Universität Berlin); Olaf Hellwich (Technical University Berlin); Andreas Ley (TU Berlin); Oleksandra Bielova (Technische Universität Berlin)

Learn Stereo, Infer Mono: Siamese Networks for Self-Supervised, Monocular, Depth Estimation, Matan Goldman (Tel Aviv University); Tal Hassner (Open University of Israel); Shai Avidan (Tel Aviv University)

IsMo-GAN: Adversarial Learning for Monocular Non-Rigid 3D Reconstruction, Soshi Shimada (DFKI); Vladislav Golyanik (MPI); Christian Theobalt (MPI Informatik); Didier Stricker (DFKI)

Aim and Scope

The full-day workshop will provide a forum for presentation of original research in computer vision and photogrammetry including the generation, processing, and analysis of 3D point clouds. Topics include, but are not limited to:

• Feature extraction, matching, and sensor orientation
• Structure from motion and SLAM
• Stereo (multi-view) and surface reconstruction
• 3D point cloud processing, segmentation, and classification
• Multi-temporal analysis, dynamic scene understanding
• Scene analysis and semantic segmentation

Organizers

• Jan-Michael Frahm, University of North Carolina at Chapel Hill, USA (jmf@cs.unc.edu)
• Andrea Fusiello, Università degli Studi di Udine, Italy (andrea.fusiello@uniud.it)
• Ronny Hänsch, Technische Universität Berlin, Germany (r.haensch@tu-berlin.de)
• Alper Yilmaz, The Ohio State University, USA (yilmaz.15@osu.edu)

Program Committee

• Panagiotis Agrafiotis, National Technical University of Athens
• Federica Arrigoni, TU Prague
• Kalle Åström, Lund University
• Mathieu Brédif, IGN
• Francesco Fassi, Politecnico di Milano
• Markus Gerke, Technische Universität Braunschweig
• Guy Godin, National Research Council Canada
• Diego Gonzalez-Aguilera, University of Salamanca
• Venu Govindu, Indian Institute of Science
• Michael Gruber, Vexcel Imaging GmbH
• Siavash Hosseinyalamdary, University of Twente
• Nathan Jacobs, University of Kentucky
• Martin Kada, TU-Berlin
• Vladimir Knyaz, State research Institute of Aviation Systems
• Vincent Lepetit, TU Graz
• Hongdong Li, Australian National University (ANU)
• Roderik Lindenbergh, Delft University of Technology
• Luca Magri, Teledyne Optech
• Clément Mallet, IGN
• Eleonora Maset, University of Udine
• Fabio Menna, Comex Innovation
• Philippos Mordohai, Stevens Institute of Technology
• Erica Nocerino, Bruno Kessler Foundation
• Hayko Riemenschneider, Disney Research
• Fulvio Rinaudo, Politecnico di Torino
• Stuart Robson, University College London
• Ribana Roscher, University of Bonn
• Franz Rottensteiner, Leibniz Universität Hannover
• Mozhdeh Shahbazi, University of Calgary
• Sudipta Sinha, Microsoft Research
• Dimitrios Skarlatos, Cyprus University of Technology
• Noah Snavely, Cornell University
• Cyrill Stachniss, University of Bonn
• Akihiro Sugimoto, National Institute of Informatics
• Bruno Vallet, IGN
• Geert Verhoeven, Ludwig Boltzmann Gesellschaft GmbH
• Yury Vizilter, State Research Institute of Aviation Systems
• Michele Volpi, ETH Zurich
• Jan Dirk Wegner, ETH Zurich
• Martin Weinmann, Karlsruhe Institute of Technology

Paper Submission

All submissions will be handled electronically via: http://cmt3.research.microsoft.com/PCV2019/

Submission deadline is March 4 March 12 (extended), 2019, 23:59 (GMT). Papers are limited to eight pages, including figures and tables, in the CVPR style. Additional pages containing only cited references are allowed. Please refer to the following files for detailed formatting instructions:

• Example submission paper with detailed instructions: egpaper_for_review.pdf
• LaTeX/Word Templates (zip): PCV2019AuthorKit.zip

Policies

The submission deadline and the page limit are strict. Manuscripts with more than 8 pages (excluding references), or which are received after the deadline, will be rejected without review.

Reviewing is double blind, in that authors do not know the names of the reviewers and reviewers do not know the names of the authors. Please read Section 1.6 of the example paper egpaper_for_review.pdf for detailed instructions on how to preserve anonymity. Avoid providing acknowledgments or links that may identify the authors.

By submitting a manuscript, the authors guarantee that it has not been previously published or accepted for publication in substantially similar form. Furthermore, no paper which contains significant overlap with the contributions of this paper either is under review at the moment of submission or will be submitted during the review period to any other conference, workshop or journal.

Please note however, that papers that are at most 4 pages *including references* do not count as a dual submission according to CVPR and ICCV rules. Therefore, such papers can be submitted to PCV even if they are submitted/accepted at CVPR or ICCV.

Registration

Registration for PCV 2019 is handled through the local conference website. Please visit the conference site also for any additional information, such as venue and travel information, nearby accommodation, and the full conference program.

Dates

• Paper submission deadline: March 4, 2019 March 12, 2019 (extended)
• Notification to authors: April 3, 2019
• Camera-ready deadline: April 10, 2019 April 15, 2019
• Workshop: June 17, 2019