3D Metric Rectification using Angle Regularity

Abstract
We propose Automatic Metric Rectification of projectively distorted 3D structures for man-made scenes using Angle Regularity. Man-made scenes, such as buildings, are characterized by a profusion of mutually orthogonal planes and lines. Assuming the availability of planar segmentation, we search for the rectifying 3D homography  which maximizes the number of orthogonal plane-pairs in the structure. We formulate the orthogonality constraints in terms of the Absolute Dual Quadric (ADQ). Using RANSAC, we first estimate the ADQ which maximizes the number of planes meeting at right angles. A rectifying homography recovered from the ADQ is then used as an initial guess for nonlinear refinement. Quantitative experiments show that the method is highly robust to the amount of projective distortion, the number of outliers (i.e. non-orthogonal planes) and noise in structure recovery. Unlike previous literature, this method does not rely on any knowledge of the cameras or images, and no global model, such as Manhattan World, is imposed.

Publication
Aamer Zaheer, Sohaib Khan, “3D Metric Rectification using Angle Regularity”, IEEE Winter Conference on Applications of Computer Vision (WACV), 2014.

Results

Code for Shape from Angle Regularity and its results can be found on SfAR page.
Code Coming Soon.