Elastic Prior Shape Models of 3D Objects for Bayesian Image Analysis

2011 ◽  
Vol 38 (1) ◽  
pp. 29-46 ◽  
Author(s):  
Fahimah Al-Awadhi ◽  
Merrilee Hurn ◽  
Christopher Jennison

1997 ◽  
Vol 1 (1) ◽  
pp. 63-77 ◽  
Author(s):  
K. V. Mardia

Bayes' theorem is a vehicle for incorporating prior knowledge in updating the degree of belief in light of data. For example, the state of tomorrow's weather can be predicted using belief or likelihood of tomorrow's weather given today's weather data. We give a brief review of the recent advances in the area with emphasis on high-level Bayesian image analysis. It has been gradually recognised that knowledge-based algorithms based on Bayesian analysis are more widely applicable and reliable than ad hoc algorithms. Advantages include the use of explicit and realistic statistic models making it easier to understand the working behind such algorithms and allowing confidence statements to be made about conclusions. These systems are not necessarily as time consuming as might be expected. However, more care is required in using the knowledge effectively for a given specific problem; this is very much an art rather than a science.


Author(s):  
Y. V. Vizilter ◽  
S. Y. Zheltov ◽  
M. A. Lebedev

Abstract. A lot of image matching applications require image comparison to be invariant relative to intensity values variations. The Pyt’ev theory for Morphological Image Analysis (MIA) was developed based on image-to-shape matching with mosaic shape models. Within the framework of this theory, the problem of shape-to-shape comparison was previously considered too. The most sophisticated and weakest part of MIA theory is the comparison of mosaic shapes with some arbitrary restrictions described by graphs or relations. In this paper we consider the possible options for comparing images and shapes using morphological projection and morphological correlation. Our contribution is a new scheme of morphological shape-to-image projection and, correspondingly, the new morphological correlation coefficient (MCC) for shape-to-image correlation with restricted mosaic models. We also refine the expressions for shape-to-shape comparison.


2015 ◽  
Vol 83 ◽  
pp. 153-167 ◽  
Author(s):  
Helia Sharif ◽  
Maxim Ralchenko ◽  
Claire Samson ◽  
Alex Ellery

Author(s):  
Shangzhe Wu ◽  
Christian Rupprecht ◽  
Andrea Vedaldi

We propose a method to learn 3D deformable object categories from raw single-view images, without external supervision. The method is based on an autoencoder that factors each input image into depth, albedo, viewpoint and illumination. In order to disentangle these components without supervision, we use the fact that many object categories have, at least approximately, a symmetric structure. We show that reasoning about illumination allows us to exploit the underlying object symmetry even if the appearance is not symmetric due to shading. Furthermore, we model objects that are probably, but not certainly, symmetric by predicting a symmetry probability map, learned end-to-end with the other components of the model. Our experiments show that this method can recover very accurately the 3D shape of human faces, cat faces and cars from single-view images, without any supervision or a prior shape model. Code and demo available at https://github.com/elliottwu/unsup3d.


Sign in / Sign up

Export Citation Format

Share Document