Welcome
to the
Stability on Watertight Models Track
of SHape Retrieval Contest 2008

Description of the track: Stability on watertight models

The aim of the track is to evaluate the stability of algorithms with respect to input perturbations such as geometric noise, varying sampling patterns or small shape deformations. The collection to search in is made of some hundreds of watertight mesh models in which various kinds of perturbations were introduced.

Meshes will be provided in two sets: the first set A contains only watertight meshes without self-intersections, whereas the second set B contains the models in A plus additional models with self-intersections. Participants must choose whether to use A or B. For participants using B, a double evaluation will be provided, one which takes into account the subset A only, and one which considers all the models in B.

Each model will be used in turn as a query against the remaining part of the database. For a given query, the goal of the track is to retrieve the most similar objects. The relevance, marginal relevance or non-relevance of the models for a given query, i.e. the ground truth, will be established a priori. The performance of the algorithms will be evaluated using the measures and tools developed for the Watertight track of SHREC'07.

Results and Summary

This track saw six registrations of which only three participants effectively sent the results of their runs. An extended summary of their results along with a commented comparison can be found in:

S.Biasotti and M. Attene, SHape REtrieval Contest 2008: Stability Track on Watertight Models, IMATI-GE / CNR, Technical Report No. 01/2008.

whereas a brief version has been published in the SMI 2008 proceedings:

S.Biasotti and M. Attene, SHREC08 Entry: Report of the Stability Track on Watertight Models, Int. Conference on Shape Modeling and Applications, IEEE Computer Society, New-York, June 4-6, 2008.