System and method for directly estimating three-dimensional structure of objects in a scene and camera motion from three two-dimensional views of the scene

A method of generating a reconstruction of at least one feature of at least one three-dimensional object in a scene from three two-dimensional views as recorded from a plurality of diverse locations, said scene reconstruction method comprising the steps of:

• A. generating in response to gradients in image intensity values at respective points in a first view and temporal derivatives of image intensity values as between second and third views and said first view values for motion parameters representing as between a first view recordation location for said first view, and view recordation locations for said second and third views;
• B. generating a dense depth map in response to the values for the motion parameters, gradients in image intensity values at respective points in a first view and temporal derivatives of image intensity values as between second and third views and said first view, the dense depth map representing for each point in the first view the depth of a corresponding point in the scene;
• and
• C. using the dense depth map in generating a reconstruction of said at least one feature.

A scene reconstruction computer program product for use in enabling a computer to generate a reconstruction of at least one feature of at least one three-dimensional object in a scene from three two-dimensional views as recorded from a plurality of diverse locations, said scene reconstruction computer program product comprising a computer-readable medium having encoded thereon:

• A. a motion parameter generator module configured to enable the computer to generate in response to gradients in image intensity values at respective points in a first view and temporal derivatives of image intensity values as between second and third views and said first view values for motion parameters representing as between a first view recordation location for said first view, and view recordation locations for said second and third views;
• B. a dense depth map generator module configured to enable the computer to generate a dense depth map in response to the values for the motion parameters, gradients in image intensity values at respective points in a first view and temporal derivatives of image intensity values as between second and third views and said first view, the dense depth map representing for each point in the first view the depth of a corresponding point in the scene;
• and
• C. a scene reconstructor module configured to enable the computer to use the dense depth map in generating a reconstruction of said at least one feature.