3DOR 2021 - Short Papers

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2633081

Browse

Browsing 3DOR 2021 - Short Papers by Issue Date

Filter results by year or month
Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Eurographics Workshop on 3D Object Retrieval: Short Papers Frontmatter
    (The Eurographics Association, 2021) Biasotti, Silvia; Dyke, Roberto M.; Lai, Yukun; Rosin, Paul L.; Veltkamp, Remco C.; Biasotti, Silvia and Dyke, Roberto M. and Lai, Yukun and Rosin, Paul L. and Veltkamp, Remco C.
  • Thumbnail Image
    Item
    SHREC 2021: Classification in Cryo-electron Tomograms
    (The Eurographics Association, 2021) Gubins, Ilja; Chaillet, Marten L.; Schot, Gijs van der; Trueba, M. Cristina; Veltkamp, Remco C.; Förster, Friedrich; Wang, Xiao; Kihara, Daisuke; Moebel, Emmanuel; Nguyen, Nguyen P.; White, Tommi; Bunyak, Filiz; Papoulias, Giorgos; Gerolymatos, Stavros; Zacharaki, Evangelia I.; Moustakas, Konstantinos; Zeng, Xiangrui; Liu, Sinuo; Xu, Min; Wang, Yaoyu; Chen, Cheng; Cui, Xuefeng; Zhang, Fa; Biasotti, Silvia and Dyke, Roberto M. and Lai, Yukun and Rosin, Paul L. and Veltkamp, Remco C.
    Cryo-electron tomography (cryo-ET) is an imaging technique that allows three-dimensional visualization of macro-molecular assemblies under near-native conditions. Cryo-ET comes with a number of challenges, mainly low signal-to-noise and inability to obtain images from all angles. Computational methods are key to analyze cryo-electron tomograms. To promote innovation in computational methods, we generate a novel simulated dataset to benchmark different methods of localization and classification of biological macromolecules in tomograms. Our publicly available dataset contains ten tomographic reconstructions of simulated cell-like volumes. Each volume contains twelve different types of complexes, varying in size, function and structure. In this paper, we have evaluated seven different methods of finding and classifying proteins. Seven research groups present results obtained with learning-based methods and trained on the simulated dataset, as well as a baseline template matching (TM), a traditional method widely used in cryo-ET research. We show that learning-based approaches can achieve notably better localization and classification performance than TM. We also experimentally confirm that there is a negative relationship between particle size and performance for all methods.
  • Thumbnail Image
    Item
    SHREC 2021: Surface-based Protein Domains Retrieval
    (The Eurographics Association, 2021) Langenfeld, Florent; Aderinwale, Tunde; Christoffer, Charles; Shin, Woong-Hee; Terashi, Genki; Wang, Xiao; Kihara, Daisuke; Benhabiles, Halim; Hammoudi, Karim; Cabani, Adnane; Windal, Feryal; Melkemi, Mahmoud; Otu, Ekpo; Zwiggelaar, Reyer; Hunter, David; Liu, Yonghuai; Sirugue, Léa; Nguyen, Huu-Nghia H.; Nguyen, Tuan-Duy H.; Nguyen–Truong, Vinh-Thuyen; Le, Danh; Nguyen, Hai-Dang; Tran, Minh-Triet; Montès, Matthieu; Biasotti, Silvia and Dyke, Roberto M. and Lai, Yukun and Rosin, Paul L. and Veltkamp, Remco C.
    Proteins are essential to nearly all cellular mechanism, and often interact through their surface with other cell molecules, such as proteins and ligands. The evolution generates plenty of different proteins, with unique abilities, but also proteins with related functions hence surface, which is therefore of primary importance for their activity. In the present work, we assess the ability of five methods to retrieve similar protein surfaces, using either their shape only (3D meshes), or their shape and the electrostatic potential at their surface, an important surface property. Five different groups participated in this challenge using the shape only, and one group extended its pre-existing algorithm to handle the electrostatic potential. The results reveal both the ability of the methods to detect related proteins and their difficulties to distinguish between topologically related proteins.
  • Thumbnail Image
    Item
    Shape Classification of Building Information Models using Neural Networks
    (The Eurographics Association, 2021) Evangelou, Iordanis; Vitsas, Nick; Papaioannou, Georgios; Georgioudakis, Manolis; Chatzisymeon, Apostolos; Biasotti, Silvia and Dyke, Roberto M. and Lai, Yukun and Rosin, Paul L. and Veltkamp, Remco C.
    The Building Information Modelling (BIM) procedure introduces specifications and data exchange formats widely used by the construction industry to describe functional and geometric elements of building structures in the design, planning, cost estimation and construction phases of large civil engineering projects. In this paper we explain how to apply a modern, low-parameter, neural-network-based classification solution to the automatic geometric BIM element labeling, which is becoming an increasingly important task in software solutions for the construction industry. The network is designed so that it extracts features regarding general shape, scale and aspect ratio of each BIM element and be extremely fast during training and prediction. We evaluate our network architecture on a real BIM dataset and showcase accuracy that is difficult to achieve with a generic 3D shape classification network.