A Comparative Survey on 3D Models Retrieval Methods

Abstract

In computer vision many studies have been conducted in order to perform the matching and comparison of 3Dmodels of objects. The main goal of matching is to group the models into different categories according to their similarityin order to allow their retrieval for recognition purposes and for further usage. So, in most of the cases, the comparisonis run on a large dataset containing various models whether they belong to the same type of object or not and generallyhaving similar or different shapes and poses. The objects nature and characteristics are important factors to be taken intoconsideration before performing the comparison step. We distinguish between two main categories of objects: rigid objectsand deformable objects whose treatment and handling differ in the modeling as well as in the comparison phases. In thispaper, we will be focusing on the comparison of deformable objects, and thus dealing with objects whose shapes mightvary in different instances. For this purpose two main approaches used in the retrieval of 3D deformable models will bereviewed and implemented: the spectral approach and the bag-of-features approach. The deformation or variation in shapeinvolves different aspects depending on the type of object. It could be a change in the posture of an articulated or bendablemodel, or it could result from a variation (loss or gain) in the total mass leading to a change in the surface and thus in theshape of the object. Even more complex situations occur when both cases are combined together.