Efficient hypercube algorithms are developed for the following image transformations: shrinking, expanding, translation, rotation, and scaling. A 2k −step shrinking and expandi...
Abstract— In this paper, we propose an arbitrary scale enlargement method of digital images based on the Laplacian pyramid (LP) representation. Through the calculation of the arb...
In recent years, 3D deformable surface reconstruction
from single images has attracted renewed interest. It has
been shown that preventing the surface from either shrinking
or s...
Mathieu Salzmann (University of California, Berkel...
This paper presents a new approach for shape description and invariant recognition by geometric-normalization implemented by neural networks. The neural system consists of a shape...