Tasks

The goal of this project is to develop a robust registration technique that adapts accurately and efficiently to the dynamic features captured from individual data. An elegant solution to it is to rely on statistical atlases generated from a set of previously registered dynamic data. This project is divided into the following four tasks:

Task 1: 4D Human data acquisition The first part of this project deals with the specification, acquisition and disseminatation of new shape data on moving humans. Such data should account for the variability in human shapes and human motions. The acquisition will be performed using the Kinovis platform at INRIA Grenoble..

Task 2: A new spatio-temporal 4D human representation We aim at developing new representations for shapes and their time evolutions in order to enable: time super-resolution to increase precision in the modeling; learning over 3D evolving shape structures; modeling the non-linearity of shapes over subject and motion variabilities; compact 4D spectral representations.

Task 3: 4D atlas construction: representations of multiple datasets of 4D data The objective here is to construct 4D human atlas which models the commonality and variability over motions and individuals, based on compact representations of multiple datasets of 4D data that are in correspondence in spatiotemporal sense.

Task 4: Representative applications Development of illustrative applications exploiting the 4D atlases’ ability on learning and inference. They will demonstrate prediction methods that, based on the 4D human atlas, are able to analyze, recover, and synthesize person- and motion-specific shape changes, from incomplete/partial data.