Motivation Recently, many researchers have begun to attempt to solve dense correspondence problem for more challenging images which have high variability in terms of photometric and/or geometric conditions [4]. For these challenging scenarios, there exist two principal bottlenecks which make conventional methods provide limited performances; (1) photometric variations derived from different cam...

A discussion of relativistic quantum–geometric mechanics on phase space and its gener-alisation to the propagation of free, massive, quantum–geometric scalar fields on curved spacetimes is given. It is shown that in an arbitrary coordinate system and frame of reference in a flat spacetime, the resulting propagator is necessarily the same as derived in the standard Minkowski coordinates up to a ...

This paper describes a geometric correction algorithm for high-resolution pushbroom type sensor images. In the systematic correction module, a sensor-orbit-Earth model was designed by using a vector projection technique which resulted in a forward transformation from raw image coordinates to geocentric coordinates . In order to avoid a large amount of computational load of the forward transform...

We propose a system that overlays textures onto the arbitrary deformable surface of an object in real time using HMD. In this system, we select a book as the object and documents as the textures. Such overlaying of textures is achieved by rendering warped textures onto a surface which is projected onto an HMD image using some geometric transformations. We assume that the surface of an object co...

Based on the differential transformation method, a semi-analytical solution is developed for free vibration and modal stress analyses of variable thickness two-directional functionally graded circular plates with restrained edges, resting on elastic foundations. Variations of the material and geometry parameters are monitored by five distinct exponential functions. The presented non-dimensional...

The analysis of collections of visual data, e.g., their classification, modeling and clustering, has become a problem of high importance in a variety of applications. Meanwhile, image data captured in uncontrolled environments by arbitrary users is very likely to be exposed to geometric transformations. Therefore, efficient methods are needed for analyzing high-dimensional visual data sets that...

Geometric graph mining has bees identified as a need in many applications. This technique detect patterns with some tolerance under a geometric transformation. To meet this need, some graph miners have been developed for detecting frequent geometric subgraphs. However, there are few works for applying this kind of geometric patterns as feature for classification tasks. In this paper, a new geom...

A geometric formulation of an important class of non-local transformations is presented. The contemporary geometric theory of Bäcklund transformations (BT) [1–4] is based on certain integrability conditions for a system of differential equations which are determine it. These equations are written in terms of connections in the submanifold of a jet-bundle foliation. One of the first nontrivial e...

We introduce gvnn, a neural network library in Torch aimed towards bridging the gap between classic geometric computer vision and deep learning. Inspired by the recent success of Spatial Transformer Networks, we propose several new layers which are often used as parametric transformations on the data in geometric computer vision. These layers can be inserted within a neural network much in the ...