SHREC'18 track: Retrieval of color pattern depicted on 3D models

The aim of this SHREC'18 track is to evaluate the performance of the retrieval algorithms when the surface of the 3D models is decorated with different color patterns (e.g. circles, squares, stripes, etc). Starting from a pre-classified dataset of “null” 3D models, a number of textures with different patterns is applied to each model. The track is organized by IMATI CNR . The SHREC'18 track: Retrieval of color pattern depicted on 3D models final report will appear, after revision, in the proceedings of the EUROGRAPHICS Workshop on 3D Object Retrieval (3DOR).

Differently from the previous tracks: SHREC’13 track: Retrieval on textured 3D models, SHREC’14 track: Retrieval and classification on textured 3D models and SHREC’15 track on shape retrieval from non rigid/textured/low quality models , in this contest we only focus on the texture-based classification of the models. The surface classification will be independent of the overall surface.

Dataset, ground truth and evaluation

The dataset consists of 300 surfaces characterized by different patterns. A model may present a single or a couple of patterns. All models are oriented, connected and locally regular, triangle meshes. Starting from a set of "null" triangle meshes, a set of color patterns has been applied to the meshes using a semi-automatic procedure. The models in the dataset are randomly shuffled. A set of examples is made available here.

Each model will be used in turn as a query against the remaining part of the database. For a given query, the goal is to retrieve the most similar objects. The relevance or non-relevance of the models for a given query, i.e. the ground truth, will be established a priori, on the basis of the pattern(s) applied to that mesh. The performance of the retrieval algorithms will be evaluated using the precision-recall curves, nearest neighbor, first tier, second tier, normalized discounted cumulated gain and average dynamic recall.

Registration and other procedures
Each participant is requested to register to the track by sending an email to Elia Moscoso Thompson (email: elia.moscoso@ge.imati.cnr.it) or Silvia Biasotti (email: silvia.biasotti@ge.imati.cnr.it) with the subject "SHREC'18 track: Retrieval of color pattern depicted on 3D models". Then, an answer will be sent to each participant with the instructions to:

Further Information

Important dates

The report on this track is ready and will be published soon!