Method and system for obtaining visual information from an image sequence using visual tunnel analysis
AssigneeMicrosoft Corporation
InventorsSing Bing Kang, Peter-Pike J. Sloan, Steven M. Seitz
Life of this patent
Estimating the term…
Loading patent…
AssigneeMicrosoft Corporation
InventorsSing Bing Kang, Peter-Pike J. Sloan, Steven M. Seitz
Estimating the term…
A method and a system for obtaining visual information from an image sequence using a visual tunnel analysis are described. The present invention determines the position and orientation of rays captured in the image sequence and uses these rays to provide visual information. This visual information includes, for example, visual prediction information (whereby the extent of visibility and appearance of a virtual camera at arbitrary locations are determined) and visual planning (whereby a minimum number of images that need to be captured to visualize a desired region is determined). Generally, the visual tunnel analysis uses a subset of the plenoptic function to determine the position and orientation of every light ray passing through each point of images in the sequence. A visual tunnel associated with an input image sequence is a volume in visibility space that represents that portion of the visibility space occupied by the input image sequence. The visual tunnel is a representation of all light rays associated with the image sequence. The present invention encodes the orientation, appearance, and density of the available light rays at every point in free space.
A method for obtaining visual information from an image sequence of scene observed by a camera, comprising:
A method for determining a range of camera poses of a scene, comprising:
A method for predicting a set of available light rays in a scene by defining a visual tunnel for an image sequence that captures at least a portion of the scene, the visual tunnel being a representation of all light rays associated with the image sequence.
A method for determining visual information from a collection of light rays, comprising:
A method for planning a camera path that will provide visualization of a desired visibility region, comprising:
A method for processing an image sequence containing at least a portion of a scene along a camera trajectory, comprising:
A method for planning a camera trajectory to capture a desired visualization of a scene, comprising:
Dependencies are inferred from the claim text.