Browsing by Author "Marin, R."

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    FARM: Functional Automatic Registration Method for 3D Human Bodies
    (© 2020 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd, 2020) Marin, R.; Melzi, S.; Rodolà, E.; Castellani, U.; Benes, Bedrich and Hauser, Helwig
    We introduce a new method for non‐rigid registration of 3D human shapes. Our proposed pipeline builds upon a given parametric model of the human, and makes use of the functional map representation for encoding and inferring shape maps throughout the registration process. This combination endows our method with robustness to a large variety of nuisances observed in practical settings, including non‐isometric transformations, downsampling, topological noise and occlusions; further, the pipeline can be applied invariably across different shape representations (e.g. meshes and point clouds), and in the presence of (even dramatic) missing parts such as those arising in real‐world depth sensing applications. We showcase our method on a selection of challenging tasks, demonstrating results in line with, or even surpassing, state‐of‐the‐art methods in the respective areas.
  • Thumbnail Image
    Item
    Matching Humans with Different Connectivity
    (The Eurographics Association, 2019) Melzi, S.; Marin, R.; Rodolà, E.; Castellani, U.; Ren, J.; Poulenard, A.; Wonka, P.; Ovsjanikov, M.; Biasotti, Silvia and Lavoué, Guillaume and Veltkamp, Remco
    Objects Matching is a ubiquitous problem in computer science with particular relevance for many applications; property transfer between 3D models and statistical study for learning are just some remarkable examples. The research community spent a lot of effort to address this problem, and a large and increased set of innovative methods has been proposed for its solution. In order to provide a fair comparison among these methods, different benchmarks have been proposed. However, all these benchmarks are domain specific, e.g., real scans coming from the same acquisition pipeline, or synthetic watertight meshes with the same triangulation. To the best of our knowledge, no cross-dataset comparisons have been proposed to date. This track provides the first matching evaluation in terms of large connectivity changes between models that come from totally different modeling methods. We provide a dataset of 44 shapes with dense correspondence as obtained by a highly accurate shape registration method (FARM). Our evaluation proves that connectivity changes lead to Objects Matching difficulties and we hope this will promote further research in matching shapes with wildly different connectivity.
  • Thumbnail Image
    Item
    Visual Assessments of Functional Maps
    (The Eurographics Association, 2019) Melzi, S.; Marin, R.; Musoni, P.; Castellani, U.; Tarini, M.; Bommes, David and Huang, Hui
    Shape-matching is one central topic in Geometry Processing, with numerous important applications in Computer Graphics and shape analysis, such as shape registration, shape interpolation, modeling, information transfer and many others. A recent and successful class of shape-matching methods is based on the functional maps framework [OBCS*12] where the correspondences between the two surfaces is described in terms of a mapping between functions. Several effective approaches have been proposed to produce accurate and reliable functional maps, leading to need for a way to assess the quality of a given solution. In particular, standard quantitative evaluation methods focus mainly on the global matching error disregarding the annoying effects of wrong correspondences along the surface details. Therefore, in this context, it is very important to pair quantitative numeric evaluations with a visual, qualitative assessment. Although this is usually not recognized as a problem, the latter task is not trivial, and we argue that the commonly employed solutions suffer from important limitations. In this work, we offer a new visual evaluation method which is based on the transfer of the object-space normals across the two spaces and then visualize the resulting lighting. In spite of its simplicity, this method produces readable images that allow subtleties of the mapping to be discerned, and improve direct comparability of alternative results.