In the context of shape and image modeling by manifold learning, we focus on the problem of denoising. A set of shapes or images being known through given samples, we capture its s...
Given a set of points corresponding to a 2D projection of a non-planar shape, we would like to obtain a representation invariant to articulations (under no self-occlusions). It is ...
Raghuraman Gopalan, Pavan K. Turaga, Rama Chellapp...
Shape grammars play an important role in a new generation of tools for the analysis and design of products. In this work we present a general tool named Shape Grammar Interpreter (...
Fitting statistical 2D and 3D shape models to images is necessary for a variety of tasks, such as video editing and face recognition. Much progress has been made on local fitting...
2D Active Appearance Models (AAM) and 3D Morphable
Models (3DMM) are widely used techniques. AAM
provide a fast fitting process, but may represent unwanted
3D transformations un...