Italian Chapter Conference 2020 - Smart Tools and Apps in computer Graphics

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2632951

Browse

Browsing Italian Chapter Conference 2020 - Smart Tools and Apps in computer Graphics by Subject "Computing methodologies"

Now showing 1 - 15 of 15
  • No Thumbnail Available
    Item
    Capturing Fonts in the Wild
    (The Eurographics Association, 2020) Kolár, Martin; Hradiš, Michal; Zemcík, Pavel; Biasotti, Silvia and Pintus, Ruggero and Berretti, Stefano
    Editing text in photographs requires the ability to find the same font, which is impossible in many settings, such as historical or manually painted text. We present a method of extracting the font from a single photographed word, without relying on the retrieval of similar fonts. A deep net extracts style information and constructs the font for all characters, enabling novel applications in image editing, font creation, and the addition of language-specific characters with diacritics to existing fonts. A qualitative user study shows that this method improves convincing font capture by over 500% over prior work.
  • No Thumbnail Available
    Item
    Comparison and Integration of Erosion Evaluation Methods for Rheumatic Degenerative Diseases
    (The Eurographics Association, 2020) Paccini, Martina; Patanè, Giuseppe; Spagnuolo, Michela; Biasotti, Silvia and Pintus, Ruggero and Berretti, Stefano
    Monitoring the development of degenerative rheumatic diseases is at the core of an efficient medical evaluation of the patient. Acquiring information on the pathology progression, indeed, helps to personalize the therapy in order to slow the pathology degeneration. Follow-up exams allow medical doctors to evaluate the situation of the patient over time. Through medical imaging scans, these exams help to identify erosion processes, which are typical indicators of a rheumatic illness. The paper presents a comparison between different methods aiming to identify erosion sites in follow-up exams. In particular, geometricbased and texture-based approaches are compared in terms of extracted information and achieved results. Finally, these two approaches are integrated in order to achieve a more complete analysis of the input anatomical district and of the underlying pathology.
  • No Thumbnail Available
    Item
    Curve Design Studio: BĂ©zier Curve Integrated Tool for Video Game Development
    (The Eurographics Association, 2020) Viagrande, Luigi Claudio; Allegra, Dario; Stanco, Filippo; Biasotti, Silvia and Pintus, Ruggero and Berretti, Stefano
    BĂ©zier curve is a useful tool for computer graphic applications. A curved road, a car, a roller coaster are just few examples of objects that could be described by a BĂ©zier curve. The video game industry already used this kind of curves in their products around the late 90', but modern game engines suffer from a lack of integrated plugin capable of manipulating and exploiting the full potential of a curve. Usually, modern game engines rely on external tools for addressing curves manipulation or they just solve some specific problems related to curves, such as animation control. In this paper we propose Curve Design Studio, a novel tool embedded in Unity3D Game Engine for assisting users to solve the main problems related to the use of curves, that may arise during the making process of a video game or any other application made with that game engine. This tool, gives the opportunity to create BĂ©zier curves easily and adapt them to many tasks, by avoiding the use of multiple external tools which solve just one specific problem. Consequently, it guarantees time-saving and lower-complexity in projects development.
  • No Thumbnail Available
    Item
    Deep-learning Alignment for Handheld 3D Acquisitions: A new Densematch Dataset for an Extended Comparison
    (The Eurographics Association, 2020) Lombardi, Marco; Savardi, Mattia; Signoroni, Alberto; Biasotti, Silvia and Pintus, Ruggero and Berretti, Stefano
    Promising solutions for the alignment of 3D views based on representation learning approaches have been proposed very recently. The potentials of these solutions that could positively affect the 3D object registration has yet to be extensively tested. In fact, a direct comparison among advisable technologies is still lacking, especially if the focus is on different data types and real-time application requirements. This work is a first contribution in this direction since we perform an independent extended comparison among prominent deep learning-driven 3D view alignment solutions by considering two relevant setups: 1) data coming from commodity 3D sensors, and 2) denser data coming from a handheld 3D optical scanner. While for the first scenario reference datasets exist, we collect and release the new benchmark dataset DenseMatch for the second setup.
  • 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.
  • No Thumbnail Available
    Item
    A First Step Towards Cage-based Deformation in Virtual Reality
    (The Eurographics Association, 2020) Scalas, Andreas; Zhu, Yuanju; Giannini, Franca; Lou, Ruding; Lupinetti, Katia; Monti, Marina; Mortara, Michela; Spagnuolo, Michela; Biasotti, Silvia and Pintus, Ruggero and Berretti, Stefano
    The advent of low cost technologies makes the use of immersive virtual environments more interesting for several application contexts. 3D models are largely used in such environments for providing feelings of immersion and presence in the virtual world. 3D models are normally defined in dedicated authoring tools and then adapted to be used in the virtual environments; thus, any change in the model requires to loop back to the authoring tool for performing the wished modification and the successive adaptation processes. The availability of shape modification capabilities within the virtual environment can avoid the above modification-adaptation loop. To this aim, we present our first step in the development of a 3D modelling system in Virtual Reality. The shape modification is achieved through a cage-based deformation approach, applied to semantically enriched meshes, carrying annotated meaningful regions, thus allowing the direct selection and editing of significant object parts.
  • No Thumbnail Available
    Item
    Kernel-Based Sampling of Arbitrary Data
    (The Eurographics Association, 2020) Cammarasana, Simone; Patanè, Giuseppe; Biasotti, Silvia and Pintus, Ruggero and Berretti, Stefano
    Point sampling is widely used in several Computer Graphics' applications, such as point-based modelling and rendering, image and geometric processing. Starting from the kernel-based sampling of signals defined on a regular grid, which generates adaptive distributions of samples with blue-noise property, we specialise this sampling to arbitrary data in terms of dimension and structure, such as signals, vector fields, curves, and surfaces. To demonstrate the novelties and benefits of the proposed approach, we discuss its applications to the resampling of 2D/3D domains according to the distribution of physical quantities computed as solutions to PDEs, and to the sampling of vector fields, 2D curves and 3D point sets. According to our experiments, the proposed sampling achieves a high approximation accuracy, preserves the features of the input data, and is computationally efficient.
  • No Thumbnail Available
    Item
    A Mesh Generation Perspective on Robust Mappings
    (The Eurographics Association, 2020) Livesu, Marco; Biasotti, Silvia and Pintus, Ruggero and Berretti, Stefano
    Mapping a shape to some parametric domain is a fundamental tool in graphics and scientific computing. In practice, a map between two shapes is commonly represented by two meshes with same connectivity and different embedding. The standard approach is to input a mesh embedded in one domain plus a set of prescribed positions for its boundary vertices in the other domain, and compute the position of the interior points in the mesh. For the 2d case, there are numerous robust tools that follow this scheme. However, theoretical issues prevent them to scale to 3d domains, thus the robust generation of volumetric maps remains an important open scientific problem. Inspired by basic principles in mesh generation, in this paper we present the reader a novel point of view on mesh parameterization. We consider connectivity as an additional unknown, and assume that our inputs are just two boundaries that enclose the domains we want to connect. We compute the map by simultaneously growing the same mesh inside both shapes in an advancing front fashion. This change in perspective allows us to recast the parameterization problem as a mesh generation problem, granting access to a wide set of mature tools that are typically not used in this setting. Our practical outcome is a provably robust yet trivial to implement algorithm that maps non convex planar shapes to convex ones. Perhaps more interestingly, we speculate on possible extensions to planar maps between non convex domains, and to volumetric maps as well, listing the major challenges that arise. Differently from prior methods, our analysis leaves us reasonable hope that an extension to volumes is possible.
  • No Thumbnail Available
    Item
    Multisided B-spline Patches Over Extraordinary Regions
    (The Eurographics Association, 2020) Hettinga, Gerben J.; Kosinka, Jiri; Biasotti, Silvia and Pintus, Ruggero and Berretti, Stefano
    We propose a generalised B-spline construction that extends uniform bi-degree B-splines to multisided regions spanned over extraordinary regions in quad-dominant meshes. We show how the structure of the existing cubic multisided B-spline patch can be generalised to work with B-spline basis functions of arbitrary degree and can be spanned over extraordinary vertices as well as extraordinary faces of quad-dominant meshes. The resulting multisided surfaces are Cd-1 continuous internally and connect with Gd-1 continuity to adjacent regular and other multisided B-splines patches. In addition, we design several specialised functions that increase the visual quality of the patches, in both the extraordinary vertex and face settings.
  • No Thumbnail Available
    Item
    Path-Traced Motion Blur using Motion Trees
    (The Eurographics Association, 2020) Martinek, Magdalena; Thiemann, Philip; Stamminger, Marc; Biasotti, Silvia and Pintus, Ruggero and Berretti, Stefano
    Motion Blur is an important effect of photo-realistic rendering. Distribution ray tracing can simulate motion blur very well by integrating light, both over the spatial and the temporal domain. However, increasing the problem by the temporal dimension entails many challenges, particularly in cinematic multi-bounce path tracing of complex scenes where heavy-weight geometry with complex lighting and even offscreen elements contribute to the final image. In particular, for fast moving objects, undersampling in the time domain results in severe artefacts. In this paper, we propose the Motion Tree, a novel Level-of-Detail data structure for efficient handling of animated objects, that both filters in the spatial and the temporal domain. The Motion Tree is a compact nesting of a temporal interval binary tree for filtering time consecutive data and a sparse voxel octree (SVO) which simplifies spatially nearby data. It is generated during a pre-process and fits nicely into any conventional physically based path tracer. When used in a production-scale environment it significantly reduces memory requirements allowing for a speedup in rendering performance with user control over the degree of impact on quality.
  • No Thumbnail Available
    Item
    Point to Culture: a Point to Click Framework for Serious Games in Cultural Heritage
    (The Eurographics Association, 2020) Viagrande, Luigi Claudio; Allegra, Dario; Stanco, Filippo; Biasotti, Silvia and Pintus, Ruggero and Berretti, Stefano
    In this paper we propose Point to Culture, a novel plugin for Unity3D game engine which allows the realisation of simple yet beautiful and historically rich Serious Games in the form of point-to-click adventures, a type of game that is well suited for Cultural Heritage dissemination and promotion. Given the ever growing demand for technologies which enhance Cultural Heritage Serious Games, we provided a complete and modular plugin for one of the most common game engine which allows the development of a game, like an escape room, with almost no line of code needed. Additionally, in order to test the proposed tool, we present a case-study game set in the Benedictine Monastery of Catania.
  • No Thumbnail Available
    Item
    Recognition, Modelling and Interactive Manipulation of Motifs or Symbols Represented by a Composition of Curves
    (The Eurographics Association, 2020) Romanengo, Chiara; Brunetto, Erika; Biasotti, Silvia; Catalano, Chiara Eva; Falcidieno, Bianca; Biasotti, Silvia and Pintus, Ruggero and Berretti, Stefano
    In this work we introduce a method for the recognition, modelling and interactive manipulation of graphical motifs, symbols or artistic elements that are represented by a composition of plane curves. Our method bases on Hough transform (HT) concepts, in particular on its generalisation to algebraic curves. We recognise complex curves and their compositions starting from images or point clouds, we represent them in implicit or parametric form, and their parameters are calculated together with their relationships. Besides the recognition of curves and modelling by algebraic equations, we propose a visualisation and manipulation tool developed on a multi-touch table. The objective of this application is to support an interactive manipulation of any geometric motifs or symbols with or without imposing the constraints derived from the identified relations among the curve parameters. Finally, we validate the proposed method showing its application to three detailed case studies, which differ in type and creation mode.
  • No Thumbnail Available
    Item
    A System for Fast and Scalable Point Cloud Indexing Using Task Parallelism
    (The Eurographics Association, 2020) Bormann, Pascal; Krämer, Michel; Biasotti, Silvia and Pintus, Ruggero and Berretti, Stefano
    We introduce a system for fast, scalable indexing of arbitrarily sized point clouds based on a task-parallel computation model. Points are sorted using Morton indices in order to efficiently distribute sets of related points onto multiple concurrent indexing tasks. To achieve a high degree of parallelism, a hybrid top-down, bottom-up processing strategy is used. Our system achieves a 2.3x to 9x speedup over existing point cloud indexing systems while retaining comparable visual quality of the resulting acceleration structures. It is also fully compatible with widely used data formats in the context of web-based point cloud visualization. We demonstrate the effectiveness of our system in two experiments, evaluating scalability and general performance while processing datasets of up to 52.5 billion points.
  • No Thumbnail Available
    Item
    ViDA 3D: Towards a View-based Dataset for Aesthetic prediction on 3D models
    (The Eurographics Association, 2020) Angelini, Mattia; Ferrulli, Vito; Banterle, Francesco; Corsini, Massimiliano; Pascali, Maria Antonietta; Cignoni, Paolo; Giorgi, Daniela; Biasotti, Silvia and Pintus, Ruggero and Berretti, Stefano
    We present the ongoing effort to build the first benchmark dataset for aestethic prediction on 3D models. The dataset is built on top of Sketchfab, a popular platform for 3D content sharing. In our dataset, the visual 3D content is aligned with aestheticsrelated metadata: each 3D model is associated with a number of snapshots taken from different camera positions, the number of times the model has been viewed in-between its upload and its retrieval, the number of likes the model got, and the tags and comments received from users. The metadata provide precious supervisory information for data-driven research on 3D visual attractiveness and preference prediction. The paper contribution is twofold. First, we introduce an interactive platform for visualizing data about Sketchfab. We report a detailed qualitative and quantitative analysis of numerical scores (views and likes collected by 3D models) and textual information (tags and comments) for different 3D object categories. The analysis of the content of Sketchfab provided us the base for selecting a reasoned subset of annotated models. The second contribution is the first version of the ViDA 3D dataset, which contains the full set of content required for data-driven approaches to 3D aesthetic analysis. While similar datasets are available for images, to our knowledge this is the first attempt to create a benchmark for aestethic prediction for 3D models. We believe our dataset can be a great resource to boost research on this hot and far-from-solved problem.
  • No Thumbnail Available
    Item
    Working with Volumetric Meshes in a Game Engine: a Unity Prototype
    (The Eurographics Association, 2020) Pitzalis, Luca; Cherchi, Gianmarco; Scateni, Riccardo; Spano, Lucio Davide; Biasotti, Silvia and Pintus, Ruggero and Berretti, Stefano
    Volumetric meshes are useful assets in many different research and application fields, like physical simulations, FEM or IGA. In the last decade, the Computer Graphics community dedicated a lot of effort in studying and developing new algorithms for the creation, manipulation, and visualization of this family of meshes. In the meantime, Game Development became a relevant field of application for CG practitioners entangled with AR and VR techniques. In this work, we position ourselves at the confluence of these two broad research and development paths. We introduce a custom data structure aiming at using volumetric meshes in Unity. To this purpose, we combine gaming techniques and interactions with typical operations of volumetric meshes. Besides this, to make the researcher experience more realistic, we also introduce features to manipulate volumetric meshes for their projects in an immersive environment using VR techniques. We think this feature can be useful in developing tools for 3D Sculpting or Digital Fabrication.