Learning Category-Specific Deformable 3D Models for Object Reconstruction

Learning Models for 3d Object-category Recognition

Globally constrained deformable models for 3D object reconstruction

To achieve geometric reconstruction from 3D datasets two complementary approaches have been widely used. On one hand the deformable model framework locally applies forces to t the data. On the other hand, the non-rigid registration framework computes a global transformation minimizing the distance between a template and the data. We rst show that applying a global transformation on a surface te...

Deformable 3D Reconstruction with an Object Database

Deformable 3D reconstruction from 2D images requires prior knowledge on the scene structure. Template-free methods [1, 2, 5, 6, 9, 14] use generic prior knowledge such as piecewise smoothness but require multiple images with significant baseline. Template-based methods [4, 10, 13] require only one image but handle only one object for which they need specific prior knowledge, namely a 3D templat...

Learning deformable shape models for object tracking

The use of computer vision to locate or track objects in images has applications in a diversity of domains. It is generally recognised that the analysis of objects of interest is eased signi cantly by making use of models of objects. In many cases, the strongest visual feature of an object is its shape. Also, many objects of interest are non-rigid, or have a non-rigid appearance with respect to...

Tomographic reconstruction using 3D deformable models.

We address the issue of reconstructing the shape of an object with uniform interior activity from a set of projections. We estimate directly from projection data the position of a triangulated surface describing the boundary of the object while incorporating prior knowledge about the unknown shape. This inverse problem is addressed in a Bayesian framework using the maximum a posteriori (MAP) es...