3DOR 14

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/7710

Browse

Browsing 3DOR 14 by Subject "Content Analysis and Indexing"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Retrieval and Classification on Textured 3D Models
    (The Eurographics Association, 2014) Biasotti, S.; Cerri, A.; Abdelrahman, M.; Aono, M.; Hamza, A. Ben; El-Melegy, M.; Farag, A.; Garro, V.; Giachetti, A.; Giorgi, D.; Godil, A.; Li, C.; Liu, Y.-J.; Martono, H. Y.; Sanada, C.; Tatsuma, A.; Velasco-Forero, S.; Xu, C.-X.; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
    This paper reports the results of the SHREC'14 track: Retrieval and classification on textured 3D models, whose goal is to evaluate the performance of retrieval algorithms when models vary either by geometric shape or texture, or both. The collection to search in is made of 572 textured mesh models, having a two-level classification based on geometry and texture. Together with the dataset, a training set of 96 models was provided. The track saw eight participants and the submission of 22 runs, to either the retrieval or the classification contest, or both. The evaluation results show a promising scenario about textured 3D retrieval methods, and reveal interesting insights in dealing with texture information in the CIELab rather than in the RGB colour space.
  • Thumbnail Image
    Item
    Towards the Extraction of Hierarchical Building Descriptions from 3D Indoor Scans
    (The Eurographics Association, 2014) Ochmann, Sebastian; Vock, Richard; Wessel, Raoul; Klein, Reinhard; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
    We present a new method for the hierarchical decomposition of 3D indoor scans and the subsequent generation of an according hierarchical graph-based building descriptor. The hierarchy consists of four basic levels with according entities, building - storey - room - object. All entities are represented as attributed nodes in a graph and are linked to the upper level entity they are located in. Additionally, nodes of the same level are linked depending on their spatial and topological relationship. The hierarchical description enables easy navigation in the formerly unstructured data, measurement takings, as well as carrying out retrieval tasks that incorporate geometric, topological, and also functional building properties describing e.g. the designated use of single rooms according to the objects it contains. In contrast to previous methods which either focus on the segmentation into rooms or on the recognition of indoor objects, our holistic approach incorporates a rather large spectrum of entities on different semantic levels that are inherent to 3D building representations. In our evaluation we show the feasibility of our method for extraction of hierarchical building descriptions for various tasks using synthetic as well as real world data.
  • Thumbnail Image
    Item
    TreeSha: 3D Shape Retrieval with a Tree Graph Representation based on the Autodiffusion Function Topology
    (The Eurographics Association, 2014) Garro, Valeria; Giachetti, Andrea; Benjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkamp
    In this paper we present a new method for shape description and matching based on a tree representation built upon the scale space analysis of maxima of the Autodiffusion function (ADF). The use of the Heat Kernel based approach makes the method invariant to articulated deformations. By coupling maxima of the Autodiffusion function with the related basins of attraction, it is possible to link the information at different scales encoding spatial relationships in a tree structure. Furthermore, texture information can be easily included in the descriptor by adding regional color histograms to the node attributes of the tree. Dedicated graph kernels have been designed to evaluate shape dissimilarity from the obtained representations using both structural, geometric and color information. Preliminary experiments performed on the SHREC 2013 non-rigid textured dataset showed very good retrieval performances.