<title>3D object recognition based on hierarchical eigen shapes and Bayesian inference</title>

Abstract

We present results of using Bayesian inference for recovering the 3-D shape and texture of an object based on information extracted from a single 2-D image. We are using a number of different models for specific object classes. The goal is to combine the classes to a hierarchical structure. Instead of searching for the most probable explanation we estimate the entire posterior distribution of the model parameters using Markov chain Monte Carlo methods. The evaluation of model fit is based on combining edge information with intensity difference between the model and the target image.

Estimation of orientation of a textured planar surface using projective equations and separable analysis with M-channel wavelet decomposition

“…Estimating the orientation of a planar texture surface finds various applications in the problem domain of "shape from texture". Detection and recovery of 3-D shape and structure of regular solid objects [6,20,23,36], scene geometry (indoor and outdoor) and environment mapping [15,27,33], scene homography estimation for perspective distortion corrections [6,7,16] and 3-D object recognition [24,32,41] are some of the important applications for this task. from 3-D shape"; and (ii) 3-D variations of a corrugated surface with height variations (called "3-D texture" [8]).…”