Shape-Adapted Smoothing in Estimation of 3-D Depth Cues from Affine Distortions of Local 2-D Brightness Structure
Tony Lindeberg and Jonas GardingTechnical report ISRN KTH/NA/P--93/35--SE.
Shortened version in Proc. 3rd European Conf. on Computer Vision, (Stockholm, Sweden), May 2--5, 1994. In: Springer-Verlag Lecture Notes in Computer Science, vol.~800, pp.~389--400.
Extended version Image and Vision Computing, vol. 15, pp. 415--434, 1997.
AbstractRotationally symmetric operations in the image domain may give rise to shape distortions. This article describes a way of reducing this effect for a general class of methods for deriving 3-D shape cues from 2-D image data, which are based on the estimation of locally linearized distortion of brightness patterns. By extending the linear scale-space concept into an affine scale-space representation and performing affine shape adaption of the smoothing kernels, the accuracy of surface orientation estimates derived from texture and disparity cues can be improved by typically one order of magnitude. The reason for this is that the image descriptors, on which the methods are based, will be relative invariant under affine transformations, and the error will thus be confined to the higher-order terms in the locally linearized perspective mapping.
Conference paper: (PDF)
Extended journal paper: (PDF)
Related work: (Shape from texture using second-moment matrices) (Shape from disparity gradients using second-moment matrices) (Combined framework for direct computation of shape cues from local image deformations) (Application of shape adaptation to fingerprint enhancement) (Monograph on scale-space theory) (Other publications on scale-space theory) (Encyclopedia entry on scale-space theory)
Responsible for this page: Tony Lindeberg