ICCV'07 Workshop on
         Photometric Analysis For Computer Vision
                         PACV 2007

              Oct 14, 2007, Rio de Janeiro, Brazil

             http://pacv2007.inrialpes.fr/Home.html


NEWS!  ===========================================================

  - Submission Site is now open: http://pacv2007-review.inrialpes.fr/

  - Two Prizes are going to be awarded to the best papers of the workshop:
      * A Best Paper Award: jumi,500.00
		   (all the papers submitted are candidat)
      * A Best Student Paper Award:  jumi,000.00
                    (only papers of which the first author is a PhD
                     candidate can apply to this award)

  - Paper Submission Deadline is: Aug. 3rd, 2007, 11:00 AM UTC/GMT +1h
	=> there will be no deadline extension !
	=> Intention of submission deadline is July 30th, 2007


PACV 2007 information:  ========================================
=> Complete information can be found at http://pacv2007.inrialpes.fr/
================================================================

Organizing Committee:

     Peter Belhumeur, Program Chair, Columbia University, USA
     Katsushi Ikeuchi, Program Chair, University of Tokyo, Japan
     Emmanuel Prados, Organizer & General Co-Chair, INRIA, France
     Stefano Soatto, General Chair, UCLA, USA
     Peter Sturm, Organizer & Program Chair, INRIA, France

Program Committee:

     Edward H. Adelson,    Massachusetts Institute of Technology, USA
     Ronen Basri,          The Weizmann Institute of Science, Israel
     Daniel Cremers,       University of Bonn, Germany
     Mark S. Drew,         Simon Fraser University, Canada
     Graham Finlayson,     University of East Anglia, UK
     David Forsyth,        U.C. Berkeley, USA
     William T. Freeman,   Massachusetts Institute of Technology, USA
     Theo Gevers,          University of Amsterdam, Netherlands
     Edwin R. Hancock,     University of York, UK
     Anders Heyden,        Lund Institute of Technology, Sweden
     David W. Jacobs,      University of Maryland, USA
     Jan J. Koenderink,    Utrecht University, The Netherlands
     Ryszard S. Kozera,    University of Western Australia, Australia
     David J. Kriegman,    University of California, San Diego, USA
     Kyros Kutulakos,      University of Toronto, Canada
     Mike Langer,          McGill, Canada
     Sang Wook Lee,        Sogang University, Korea
     Hendrik Lensch,       Max-Planck-Institut, Germany
     Steve Lin,            Microsoft Research Asia
     Shree K. Nayar,       Columbia University, USA
     Marc Pollefeys,       University of North Carolina, USA
     Jean Ponce,           INRIA, France
     Yoichi Sato,          University of Tokyo, Japan
     Steven Seitz,         University of Washington, USA
     Jan Erik Solem,       Malmö University, Sweden
     Todd Zickler,         Harvard University, USA

Important Dates:

Intention of submission         July 30th, 2007
Deadline for paper submission   August 3rd, 2007  11:00 AM UTC/GMT +1h
Notification of acceptance      September 14th, 2007
Camera-ready copies due to      September 30th, 2007
Conference dates                October 14th, 2007
Journal submission              January, 2008.

Submission:  see http://pacv2007.inrialpes.fr/Submissions.html

Scope:
======

The way an image looks like depends on many factors, including geometry, 
illumination and reflectance properties of the objects. For the 
transparent or translucent objects, or for the objects composed by 
multiple coatings, the factors are even more numerous (refraction, 
subsurface scattering,...). The laws combining these components are very 
diverse and complex. This complexity makes computer vision tasks even 
more difficult and practically causes the failure of methods based on 
too simple models.

A typical example could be the troubles caused by the specularities in 
the stereo-vision problem; proposed methods usually assume that the 
scene in perfectly diffuse. Feature tracking/matching is another example 
since the photometric appearance of the objects can change when they/the 
camera move/es.

 From the theoretical as well as from the computational point of view, a 
better understanding and handling of these factors and of their 
combinations should allow to be robust to the photometric effects. In 
fact this allows us to go beyond: it allows not only to overcome the 
inconveniences problems they involve but it can also be an 
information/constraints source which can be practically exploited in 
computer vision tasks. We can think for example about the shading and 
shadow information.

More synthetically, the topics of interest include, but are not limited 
to, the following:
    1. Theoretical Analysis:
         - image invariants,
         - characterization of ambiguities (e.g. viewpoint-lighting
           ambiguity, characterization of the solutions of a problem).
         - number of images required for solving computer vision tasks.
    2. Insensitivity to the appearance changes:
         - image invariants.
         - taking into account appearance changes in models (e.g. in 3D
           reconstruction, feature matching/tracking, segmentation).
    3. Separation/reconstruction:
         - recovering reflectance properties and lighting conditions for
           realistic changes of point of view
         - improvement of images: removing highlights, relighting,
           modification of the albedo (application: advertisement)...
    4. Exploitation:
         - exploitation of shading and shadows (e.g. in Shape from
           Shading, in stereo-vision when point correspondence is
           difficult or impossible)
         - exploitation of the appearance changes (e.g. in photometric
           stereo)

The spectrum of considered applications covers the following non 
comprehensive list:
     - Shape estimation: Multiple view geometry, shape from shading,
       Stereoscopic segmentation, photometric stereo...
     - Radiance/lighting estimation: separation of
       geometry/reflectance/illumination, image improvement...
     - Recovery of complete and high quality models
     - Feature extraction, feature matching/tracking, object
       tracking/recognition, Segmentation...

Miscellaneous:
    1. Selected Papers from the Workshop will appear in a special issue 
of the International Journal of Computer Vision
    2. Proceedings will be published by IEEE.