Home Call for Papers Important Dates Submissions Final Program Registration and Hotel Invited Speakers People Sponsors Previous Meetings

Invited Speakers Andrew Blake Microsoft Research, Cambridge, UK Interactive image editing -- powered by Computer Vision Advances in computer vision in the last 2 decades have had a profound effect on interactive computer graphics, to the extent that many, if not most, new algorithms for image interaction in graphics have their roots in Computer Vision techniques. Perhaps the first influential development of this kind was LiveWire or Intelligent Scissors, derived from research on Snakes around 1990. The vision groups at Microsoft Research have been able to develop and exploit more recent technologies in machine vision including graph-cut, Markov Random fields and non-parametric texture models. This has led to practical interactive image editing tools that are both powerful and simple to use. Tools already commercialized include smart cloning ("Blender"), object removal ("PatchWorks"), Panorama stitching and automated cut and paste ("GrabCut"), with others in the pipeline including "Guided PatchWorks", "Markov Image Distance", "Tapestry" and others. Shree K. Nayar Columbia University, NYC, US Visual Chatter in the Real World When a scene is lit by a source of light, the brightness of each point in the scene can be viewed as having two components, namely, direct and global. The direct component is due to the direct illumination of the point by the source. The global component is due to the illumination of the point by other points in the scene. The global component can arise from various effects, including, interreflections, subsurface scattering and volumetric scattering. In this talk, I will present a fast method for separating the direct and global components of a scene measured by a camera and illuminated by a light source. This separation method has been applied to a wide variety of real-world objects. The resulting direct and global images reveal surprising interactions of light within as well as between objects. I will show results for living objects (skin, leaves, flowers, etc.) as well as inanimate ones (marble, clay, cloth, etc.).