Unsupervised Learning of Object Deformation Models Supplemental Material
نویسندگان
چکیده
Non-trivial deformations result in local contractions and expansions. These naturally capture object scalings but can have a negative side effect, namely making object features disappear or inflate. For this reason we want the deformation fields to have zero acceleration in the direction perpendicular to image features; this guarantees that the features are only ‘transported’. This requirement can be phrased as follows: consider a deformation field h = (hx, hy) = (x + fx, y + fx); fx and fy are the deformation increments calculated from the linear basis synthesis. Along orientation nx, ny this deformation field has ‘speed’ fxnx + fyny; a constant speed means that the motion of features in this orientation does not distort them, i.e. it is purely translating them. We can thus enforce our constraint by requiring that the directional derivative of this speed function equals zero, i.e.
منابع مشابه
An Unsupervised Learning Method for an Attacker Agent in Robot Soccer Competitions Based on the Kohonen Neural Network
RoboCup competition as a great test-bed, has turned to a worldwide popular domains in recent years. The main object of such competitions is to deal with complex behavior of systems whichconsist of multiple autonomous agents. The rich experience of human soccer player can be used as a valuable reference for a robot soccer player. However, because of the differences between real and simulated soc...
متن کاملLearning probabilistic deformation models from image sequences
In this paper, we present an approach for an unsupervised learning of probabilistic deformation modes of 2D moving objects from image sequences. The object representation relies on a statistical description of global and local deformations applied to an a priori prototype shape. The optimal bayesian estimate of the deformation process is obtained by maximizing a nonlinear joint probability dist...
متن کاملRecovering Articulated Object Models from 3D Range Data
We address the problem of unsupervised learning of complex articulated object models from 3D range data. We describe an algorithm whose input is a set of meshes corresponding to different configurations of an articulated object. The algorithm automatically recovers a decomposition of the object into approximately rigid parts, the location of the parts in the different object instances, and the ...
متن کاملLearning structure and deformation modes of nonrigid objects in long image sequences
In this paper, we present an original approach for an unsupervised learning of the structure and deformation modes of 2D moving objects in long image sequences. The object representation relies on a statistical description of the deformations applied to a prototype shape. The optimal bayesian estimate of the deformation process is obtained by maximizing a non-linear joint probability distributi...
متن کاملGenerative Models for 2-D images of 3-D scenes
Generative Models for 2-D images of 3-D scenes Anitha Kannan Doctor of Philosophy Graduate Department of Computer Science University of Toronto 2007 This thesis introduces generative models of appearance for analyzing 2D images of 3D visual scenes. Many 2D images contain multiple objects, where image components corresponding to each object undergo deformations, eg., due to changes in the shape ...
متن کامل