Method for reconstructing three-dimensional images from two-dimensional image data
View Patent ↗A method for reconstructing three-dimensional, plural views of images from two dimensional image data. The method includes: obtaining two-dimensional, stereo digital data from images of an object; processing the digital data to generate an initial three-dimensional candidate of the object, such process using projective geometric constraints imposed on edge points of the object; refining the initial candidate comprising examining spatial coherency of neighboring edge points along a surface of the candidate.
1. A method for reconstructing three-dimensional images from two dimensional image data, comprising:
obtaining two-dimensional, plural view, stereo digital data from images of an object;
extracting image edges and tangents from the obtained two-dimensional, plural view, stereo digital data;
processing the digital data to generate an initial three-dimensional candidate of the object, such process using projective geometric constraints imposed on edge points of the object;
defining geometric consistency between two neighboring initial candidates using differential geometric constraints on the extracted edge points and extracted tangents, including at least first order tangent continuity and, if desired, second or higher order curvature continuity;
refining the initial candidates comprising examining spatial coherency of neighboring edge points along an edge on the object using an inference algorithm and selecting a new candidate.