ShapeAdapted Smoothing in Estimation of 3D Depth Cues from Affine Distortions of Local 2D Brightness StructureTony Lindeberg and Jonas GardingTechnical report ISRN KTH/NA/P93/35SE.Shortened version in Proc. 3rd European Conf. on Computer Vision, (Stockholm, Sweden), May 25, 1994. In: SpringerVerlag Lecture Notes in Computer Science, vol.~800, pp.~389400. Extended version Image and Vision Computing, vol. 15, pp. 415434, 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 3D shape cues from 2D image data, which are based on the estimation of locally linearized distortion of brightness patterns. By extending the linear scalespace concept into an affine scalespace 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 higherorder terms in the locally linearized perspective mapping.Full paper: (PDF) (PostScript) Extended technical report: (PDF) (PostScript) Related work: (Shape from texture using secondmoment matrices) (Shape from disparity gradients using secondmoment matrices) (Combined framework for direct computation of shape cues from local image deformations) (Application of shape adaptation to fingerprint enhancement) (Monograph on scalespace theory) (Other publications on scalespace theory) (Encyclopedia entry on scalespace theory)
Responsible for this page: Tony Lindeberg
