Browsing by Author "Werghi, Naoufel"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Extracting Ordered Iso-Geodesic Points on the Mesh
    (The Eurographics Association, 2020) Tortorici, Claudio; Werghi, Naoufel; Berretti, Stefano; Biasotti, Silvia and Pintus, Ruggero and Berretti, Stefano
    The mesh manifold is one of the most used modalities for representing 3D objects. Although it provides a fully connected not oriented structure, it has some drawback when compared to the grid of pixels of a still image. Indeed, mesh manifolds do not hold any order information, neither locally nor globally, which makes some operation computationally expensive or even impossible. To unleash its potential and to benefit from its capability of representing the 3D information, further advancements have to be made in order to allow basic operations (i.e., convolution) and effective descriptor extraction. In this paper, we present our preliminary study on a new approach to extract Iso-Geodesic points on a mesh manifold. The approach can be applied in various applications, from feature extraction, to convolution operation and mesh reconstruction. It also revealed to be robust to variations of mesh surface and tessellation, providing an effective geodesic distance approximation.
  • Thumbnail Image
    Item
    Labeled Facets: New Surface Texture Dataset
    (The Eurographics Association, 2022) Ganapathi, Iyyakutti Iyappan; Werghi, Naoufel; Berretti, Stefano; Thehoaris, Theoharis; Daoudi, Mohamed; Ferrari, Claudio; Veltkamp, Remco C.
    Object detection, recognition, segmentation, and retrieval have been at the forefront of 2D and 3D computer vision for a long time and have been utilized to address various problems in interdisciplinary domains. The 3D domain has not received as much attention as the 2D domain in several of these fields, and texture analysis in 3D is one of the least investigated. In the literature, there are several classic methods for retrieving and classifying 3D textures; however, research on facet-wise texture classification and segmentation is sparse. Moreover, in recent years deep learning excels in computer vision; utilizing its capacity for 3D texture analysis could improve performance compared to classical approaches. However, the scarcity of 3D texture data makes it challenging to employ deep learning. This paper presents a labeled 3D dataset based on already existing 3D datasets that can be utilized for texture classification, segmentation, and detection. The textures in the dataset are varied, with a wide range of surface variations. The dataset provides 3D texture surfaces annotated at the facet level, as well as fundamental geometric attributes such as curvature and shape index that can be utilized directly for further analysis. Download link for the dataset https://bit.ly/3wgSQgW.
  • No Thumbnail Available
    Item
    Relief Pattern Segmentation Using 2D-Grid Patches on a Locally Ordered Mesh Manifold
    (The Eurographics Association, 2019) Tortorici, Claudio; Vreshtazi, Denis; Berretti, Stefano; Werghi, Naoufel; Agus, Marco and Corsini, Massimiliano and Pintus, Ruggero
    The mesh manifold support has been analyzed to perform several different tasks. Recently, it emerged the need for new methods capable of analyzing relief patterns on the surface. In particular, a new and not investigated problem is that of segmenting the surface according to the presence of different relief patterns. In this paper, we introduce this problem and propose a new approach for segmenting such relief patterns (also called geometric texture) on the mesh-manifold. Operating on regular and ordered mesh, we design, in the first part of the paper, a new mesh re-sampling technique complying with this requirement. This technique ensures the best trade-off between mesh regularization and geometric texture preservation, when compared with competitive methods. In the second part, we present a novel scheme for segmenting a mesh surface into three classes: texturedsurface, non-textured surface, and edges (i.e., surfaces at the border between the two). This technique leverages the ordered structure of the mesh for deriving 2D-grid patches allowing us to approach the segmentation problem as a patch-classification technique using a CNN network in a transfer learning setting. Experiments performed on surface samples from the SHREC'18 contest show remarkable performance with an overall segmentation accuracy of over 99%.