Vision Research at Washington University
Introduction
 Paolina Borghese, wife of Camillo Borghese and sister of Napoleon, posing as Venus for Antonio Canova.A roman cobblestone road in Aquileia.Giotto used occlusions to convey spatial ordering in his paintings.Surreal atmospheres are created by shadows in paintings by DeChirico.Even in absence of contextual information, we can get impressions of three-dimensionality from images.
The Sense of Vision plays a crucial role in the life of primates, allowing them to retrieve a representation of the environment that is suitable to perform complex control tasks such as moving, tracking, manipulating objects and recognizing them.  Any imaging device - whether the human eye, a video camera or a telescope - involves a map from the three-dimensional world onto the two-dimensional surface of an imaging sensor. Such a map causes a loss of information along a spatial dimension. The goal of a visual system - whether biological or artificial - is to use images to retrieve a spatial representation of the environment. MORE...
Projects
 From a sequence of moving images, it is possible to ...... estimate the motion undergone by the camera and ...... recover a three-dimensional model of the scene, which can be used to ...... render the scene as if it was viewed from a novel viewpoint.Images taken with different camera settings, for instance with different focal lengths ...... contain unequivocal information about the depth of each point in the scene.
The Vision Research Laboratory, which is part of the Electronic Signals and Systems Research Laboratory (ESSRL), is engaged in a variety of projects involving processing visual information to retrieve a model of the environment. Applications range from Image-based rendering for Virtual Reality, Archeology, CAD etc., to Guidance of Autonomous Vehicles, Human-Computer Interaction, Visualization and Recognition. Our research involves both theoretical issues in Nonlinear Estimation and Control Theory, and the realization of practical, real-time systems. MORE...
What's New!

  • Read description of our CVPR demo on the EE Times [June 2000]
  • New on-line papers [June 2000]
  • Code for real-time 3D motion and structure reconstruction available online [coming soon]
  • Reconstruction up to Subgroups gets the Marr Prize [Sept. 1999]
  • Why do fireworks seem to come towards us? [July 1999]

    		•

    PeoplePublicationsSponsorsCourses

     
    Written by Stefano Soatto (c) Washington University, 1999.