 |
    |
Parametric Manifold of an Object under Different Viewing Directions
Xiaozheng Zhang1,2, Yongsheng Gao1,2, and Terry Caelli3
1Biosecurity Group, Queensland Research Laboratory, National ICT Australia, Australia
paul.zhang@nicta.com.au
yongsheng.gao@nicta.com.au
2Computer Vision and Image Processing Lab, Griffith University, Brisbane, Australia
x.zhang@griffith.edu.au
yongsheng.gao@griffith.edu.au
http://maxwell.ict.griffith.edu.au/cvipl/
3Victoria Research Laboratory, National ICT Australia, Australia
terry.calli@nicta.com.au
Abstract. The appearance of a 3D object depends on both the viewing directions and illumination conditions. It is proven that all n-pixel images of a convex object with Lambertian surface under variable lighting from infinity form a convex polyhedral cone (called illumination cone) in n-dimensional space. This paper tries to answer the other half of the question: What is the set of images of an object under all viewing directions? A novel image representation is proposed, which transforms any n-pixel image of a 3D object to a vector in a 2n-dimensional pose space. In such a pose space, we prove that the transformed images of a 3D object under all viewing directions form a parametric manifold in a 6-dimensional linear subspace. With in-depth rotations along a single axis in particular, this manifold is an ellipse. Furthermore, we show that this parametric pose manifold of a convex object can be estimated from a few images in different poses and used to predict object’s appearances under unseen viewing directions. These results immediately suggest a number of approaches to object recognition, scene detection, and 3D modelling. Experiments on both synthetic data and real images were reported, which demonstrates the validity of the proposed representation.
Keywords: pose manifold, 3D object, in-depth rotations, viewing directions, appearance prediction, object rendering
LNCS 7576, p. 186 ff.
lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012