Abstract

In this paper we propose a probabilistic framework that mod- els shape variations and infers dense and detailed 3D shapes from a single silhouette. We model two types of shape variations, the ob ject pheno- type variation and its pose variation using two independent Gaussian Process Latent Variable Models (GPLVMs) respectively. The proposed shape variation models are learnt from 3D samples without prior knowl- edge about ob ject class, e.g. ob ject parts and skeletons, and are com- bined to fully span the 3D shape space. A novel probabilistic inference algorithm for 3D shape estimation is proposed by maximum likelihood estimates of the GPLVM latent variables and the camera parameters that best fit generated 3D shapes to given silhouettes. The proposed inference involves a small number of latent variables and it is computationally ef- ficient. Experiments on both human body and shark data demonstrate the efficacy of our new approach.