1. A Stochastic Dynamical System for Optical Flow Estimation (pdf)
    Volker Willert, Julian Eggert
  2. Kernel Spectral Curvature Clustering (KSCC) (pdf)
    Guangliang Chen, Stefan Atev, Gilad Lerman



Important Dates

Submission deadline: June 19, 2009 June 24, 2009
Notification of acceptance: July 31st, 2009
Camera ready due: August 13, 2009
Workshop date: September 28, 2009

For Workshop website issues please contact rizwanch at cis dot jhu dot edu

Call for Papers

The classical multiple-view geometry studies the case with multiple sparse images of a static scene. However, in many real-world applications, the scene may undergo complex dynamical changes (e.g., linked-rigid body or non-rigid motions) or one needs to interact with the scene through a dynamical system (e.g., vision guided robot navigation/coordination).

The confluence of computer vision and dynamical systems has initiated many interesting interdisciplinary research topics across computer vision, computer graphics, vision-based control, and unmanned vehicles.

The goal of this workshop is to converge different aspects of the research on dynamical vision and to identify common mathematical problems and methods for future research in this area by bringing together researchers from both the computer vision and automatic control communities. The workshop welcomes papers that fall into the following categories:

  • Segmentation, Estimation & Tracking of Multiple Rigid Motions.
  • Segmentation, Estimation & Tracking of Multiple Non-rigid Motions.
  • Tracking & Estimation of Linked Rigid body Motions.
  • Modeling, Identification, and Synthesis of Dynamical Scenes from Videos.
  • Structure and Range Estimation Based on Dynamical Models and Filtering Techniques.
  • Reconstruction and Parameter Estimation of Dynamical Models for Vision Applications (e.g. Surveillance, Graphics, and Robotics).

Invited Speakers


  • Richard Hartley, Australian National University
  • Stefano Soatto, University of California, Los Angeles
  • Octavia Camps, Northeastern University
  • Nuno Vasconcelos, University of California, San Diego



Paper Submission

Click here to access the submission site

Please make sure you have read the section below before you submit a paper

Paper format and length: All submissions to WDV 2009 must be electronic and in Adobe Acrobat PDF format. A complete paper should be submitted in camera-ready format. The length should match that intended for final publication. Papers accepted for the workshop will be allocated up to 8 pages in the proceedings. Authors should use the IEEE format, which can be obtained here.

Paper publication: Selected papers will be published after the workshop in the Conference DVD and IEEE Xplore. The proceedings of WDV 2005, WDV 2006 can be found here.

Double blind review: Reviews will be double blind (authors do not know the names of the reviewers of their papers, and reviewers do not know the names of the authors). In addition to removing author information from the paper header and any identity clue from the main text, every reference to work by the authors must be made anonymous in the following ways

1. Work by the same authors that appears on mainstream and readily available publications is cited in the third person, provided that nothing in the referencing can be traced to the identity of the authors. For instance, "In [3], Geman and Geman have proposed ..." is acceptable, whereas "In [3], we have proposed ..." is not.

2. Also remember to avoid information that may identify the authors in the acknowledgments (e.g. co-workers and grant IDs) and in the supplemental material (e.g. titles in the movies, or attached papers.)

Dual submission: By submitting a manuscript to WDV 2009, the authors assert that it has not been previously published in substantially similar form. ICCV 2009 allows double submissions to ICCV workshops and the main conference. Authors of a dual submission should notify the workshop organizers by e-mail before submitting. In case of double acceptance, the author(s) will have to decide where the paper should appear (main conference or workshop).

Supplemental Material: Authors may optionally upload supplemental material. Typically, this material might include videos of results that cannot be included in the main paper, anonymized related submissions to other conferences and journals, and appendices or technical reports containing extended proofs and mathematical derivations that are not essential for understanding of the paper. Note that the contents of the supplemental material should be referred to appropriately in the paper and that reviewers are not obliged to look at it. All supplemental material must be zipped or tarred into a single file and uploaded on the submission website. There is a maximum limit of 30 MB for the supplemental materials. The deadline for supplemental material is June 26th, 11:59pm, EST. Supplemental material must be in one zip file named as A< paper_number > E.g.




Prof. Anders Heyden
Department of Mathematics,
Lund University and Malmo University,


Prof. Yi Ma
Department of Electrical & Computer Engineering
University of Illinois at Urbana Champaign,


Prof. René Vidal
Department of Biomedical Engineering
Johns Hopkins University,



Prof. Ying Wu
Department of Electrical Engineering & Computer Science
Northwestern University,





Program Committee

Yannis Aloimonos

Adrien Bartoli

Octavia Camps

Xinkai Chen

Noah Cowan

Daniel Cremers

Warren Dixon

Gianfranco Doretto

Ahmed Elgammal

Paolo Favaro

Greg Hager

Richard Hartley

Kun Huang

Rolf Johansson

Fredrik Kahl

Kenichi Kanatani

Banjamin Kimia

Shmuel Peleg

Nemanja Petrovic

Stefano Soatto

Jian Sun

Nuno Vasconcelos

Lior Wolf

University of Maryland


Northeastern University

Shibaura Institute of Technology, Japan

Johns Hopkins University

University of Bonn, Germany

Clemson University

General Electric Global Research

Rutgers University

Heriot Watt University

Johns Hopkins University

Australia National University

Ohio State University

Lund University, Sweden

Lund University, Sweden

Okayama University, Japan

Brown University

Hebrew University, Israel


University California Los Angeles

Microsoft Research, Asia

University of California San Diego

Massachusetts Institute of Technology