Surface Orientation and Curvature
from Differential Texture Distortion
Shortened version in Proc. 5th International Conference
on Computer Vision, Cambridge, Massachusetts, June 1995.
A unified differential geometric framework for estimation of
local surface shape and orientation from projective texture distortion
is proposed, based on a generalization of the texture
stationarity assumption introduced by Malik & Rosenholtz.
This framework allows
the information content of the gradient of any texture descriptor
defined in a local coordinate frame
to be characterized in a very compact form.
The analysis is then specialized to three classes of texture descriptors;
full affine descriptors, the classical ``texture gradients'' and
second moment descriptors.
For estimation of local surface orientation and curvature from uncertain
observations of affine texture distortion, the proposed framework allows the
dimensionality of the search space to be reduced from five to one.