3DOR 19

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2632755

Browse

Browsing 3DOR 19 by Subject "Computer graphics"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    A 3D CAD Assembly Benchmark
    (The Eurographics Association, 2019) Lupinetti, Katia; Giannini, Franca; monti, marina; PERNOT, Jean-Philippe; Biasotti, Silvia and Lavoué, Guillaume and Veltkamp, Remco
    Evaluating the effectiveness of the systems for the retrieval of 3D assembly models is not trivial. CAD assembly models can be considered similar according to different criteria and at different levels (i.e. globally or partially). Indeed, besides the shape criterion, CAD assembly models have further characteristic elements, such as the mutual position of parts, or the type of connecting joint. Thus, when retrieving 3D models, these characteristics can match in the entire model (globally) or just in local subparts (partially). The available 3D model repositories do not include complex CAD assembly models and, generally, they are suitable to evaluate one characteristic at a time and neglecting important properties in the evaluation of assembly similarity. In this paper, we present a benchmark for the evaluation of content-retrieval systems of 3D assembly models. A crucial feature of this benchmark regards its ability to consider the various aspects characterizing the models of mechanical assemblies.
  • Thumbnail Image
    Item
    Generalizing Discrete Convolutions for Unstructured Point Clouds
    (The Eurographics Association, 2019) Boulch, Alexandre; Biasotti, Silvia and Lavoué, Guillaume and Veltkamp, Remco
    Point clouds are unstructured and unordered data, as opposed to images. Thus, most of machine learning approaches, developed for images, cannot be directly transferred to point clouds. It usually requires data transformation such as voxelization, inducing a possible loss of information. In this paper, we propose a generalization of the discrete convolutional neural networks (CNNs) able to deal with sparse input point cloud. We replace the discrete kernels by continuous ones. The formulation is simple, does not set the input point cloud size and can easily be used for neural network design similarly to 2D CNNs. We present experimental results, competitive with the state of the art, on shape classification, part segmentation and semantic segmentation for large scale clouds.