Séquences de maillages : classification et méthodes de segmentation. (Mesh sequences : classification and segmentation)

Mesh sequences are becoming a common tool in computer graphics as can be seen in video games ormedical imaging. As a consequence, mesh sequences generation’s methods have been developed. Sequences can be created using a modeler or by multi-cameras acquisition. These methods can generate sequences which have different properties. Moreover, different applications using mesh sequences have been proposed such as compression or pose transfer. Most of these applications require to compute a segmentation as a pre-processing step. This thesis deals with mesh sequence segmentation into rigid components. First, we formalize the notion of mesh sequence, and propose a nomenclature, allowing us to design the properties attached to each kind of mesh sequence, and to describe precisely what kind of sequence an algorithm requires as input. Next, we propose a formalization of mesh sequence segmentation by providing different definitions of segmentation. We then present mesh sequences segmentation state of the art. We then propose a first segmentation method, producing a global segmentation and taking as input a stable mesh sequence. This method is based on a region-growing process. Next, we present two segmentation methods, both based on spectral clustering and taking as input an unconstrained mesh sequence. The former method produces a set of global segmentations, while the latter generate either a global segmentation or a time-varying segmentation. We also propose a quantitative segmentation evaluation system. Finally, we provide future work leads on mesh sequence segmentation.