Italian Chapter Conference 2022 - Smart Tools and Apps in Graphics

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2633222
Cagliari (Italy) | 17 – 18 November 2022
Table of Contents
Software and Datasets
A Computational Tool for the Analysis of 3D Bending-active Structures Based on the Dynamic Relaxation Method
[full paper Image] [meta data Image]
Iason Manolas, Francesco Laccone, Gianmarco Cherchi, Luigi Malomo, and Paolo Cignoni
A Graphical Framework to Study the Correlation between Geometric Design and Simulation
[full paper Image] [meta data Image]
Daniela Cabiddu, Giuseppe Patané, and Michela Spagnuolo
GIM3D: A 3D Dataset for Garment Segmentation
[full paper Image] [meta data Image]
Pietro Musoni, Simone Melzi, and Umberto Castellani
Geometry Processing
PC-GAU: PCA Basis of Scattered Gaussians for Shape Matching via Functional Maps
[full paper Image] [meta data Image]
Michele Colombo, Giacomo Boracchi, and Simone Melzi
Topological Initialization of Injective Integer Grid Maps
[full paper Image] [meta data Image]
Marco Livesu
Nearly Smooth Differential Operators on Surface Meshes
[full paper Image] [meta data Image]
Claudio Mancinelli and Enrico Puppo
Outside-in Priority-based Approximation of 3D Models in LEGO Bricks
[full paper Image] [meta data Image]
Filippo Andrea Fanni, Elisa De Rossi, and Andrea Giachetti
Rendering and Visualization
Accurate Molecular Atom Selection in VR
[full paper Image] [meta data Image]
Elena Molina and Pere-Pau Vázquez
Enforcing Energy Preservation in Microfacet Models
[full paper Image] [meta data Image]
Davide Sforza and Fabio Pellacini
Versatile Geometric Flow Visualization by Controllable Shape and Volumetric Appearance
[full paper Image] [meta data Image]
Mahmoud Zeidan, Christoph Peters, Tobias Rapp, and Carsten Dachsbacher
Optimizing Placements of 360° Panoramic Cameras in Indoor Environments by Integer Programming
[full paper Image] [meta data Image]
Syuan-Rong Syu and Chi-Han Peng
Posters
Creating Adaptive and Interactive Stories in Mixed Reality
[full paper Image] [meta data Image]
Vittoria Frau, Sergio Serra, and Lucio Davide Spano
Deep Tracking for Robust Real-time Object Scanning
[full paper Image] [meta data Image]
Marco Lombardi, Mattia Savardi, and Alberto Signoroni
Floor Plan Exploration Framework Based on Similarity Distances
[full paper Image] [meta data Image]
Chia-Ying Shih and Chi-Han Peng
Multiple Scattering Approximation for Real-time Underwater Spectral Rendering
[full paper Image] [meta data Image]
Néstor Monzón, Derya Akkaynak, Diego Gutiérrez, and Adolfo Muñoz
MUSE: Modeling Uncertainty as a Support for Environment
[full paper Image] [meta data Image]
Marianna Miola, Daniela Cabiddu, Simone Pittaluga, and Marino Vetuschi Zuccolini
ProMED: Production Optimization for Additive Manufacturing of Medical Devices
[full paper Image] [meta data Image]
Marco Attene, Tiziano Berti, Daniela Cabiddu, Antonio Garosi, Marco Livesu, Zsolt Pasztor, Daniel Petrovszki, and Andrea Ranieri
Machine Learning for Graphics
SPIDER: SPherical Indoor DEpth Renderer
[full paper Image] [meta data Image]
Muhammad Tukur, Giovanni Pintore, Enrico Gobbetti, Jens Schneider, and Marco Agus
CAD 3D Model Classification by Graph Neural Networks: A new Approach based on STEP Format
[full paper Image] [meta data Image]
Lorenzo Mandelli and Stefano Berretti
An Interactive Tuning Method for Generator Networks Trained by GAN
[full paper Image] [meta data Image]
Mengyuan Zhou and Yasushi Yamaguchi

BibTeX (Italian Chapter Conference 2022 - Smart Tools and Apps in Graphics)
@inproceedings{
10.2312:stag.20222020,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference: Frontmatter}},

author = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20222020}

}
@inproceedings{
10.2312:stag.20221251,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
A Graphical Framework to Study the Correlation between Geometric Design and Simulation}},

author = {
Cabiddu, Daniela
 and 
Patané, Giuseppe
 and 
Spagnuolo, Michela
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221251}

}
@inproceedings{
10.2312:stag.20221250,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
A Computational Tool for the Analysis of 3D Bending-active Structures Based on the Dynamic Relaxation Method}},

author = {
Manolas, Iason
 and 
Laccone, Francesco
 and 
Cherchi, Gianmarco
 and 
Malomo, Luigi
 and 
Cignoni, Paolo
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221250}

}
@inproceedings{
10.2312:stag.20221252,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
GIM3D: A 3D Dataset for Garment Segmentation}},

author = {
Musoni, Pietro
 and 
Melzi, Simone
 and 
Castellani, Umberto
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221252}

}
@inproceedings{
10.2312:stag.20221253,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
PC-GAU: PCA Basis of Scattered Gaussians for Shape Matching via Functional Maps}},

author = {
Colombo, Michele
 and 
Boracchi, Giacomo
 and 
Melzi, Simone
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221253}

}
@inproceedings{
10.2312:stag.20221254,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
Topological Initialization of Injective Integer Grid Maps}},

author = {
Livesu, Marco
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221254}

}
@inproceedings{
10.2312:stag.20221256,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
Outside-in Priority-based Approximation of 3D Models in LEGO Bricks}},

author = {
Fanni, Filippo Andrea
 and 
Rossi, Elisa De
 and 
Giachetti, Andrea
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221256}

}
@inproceedings{
10.2312:stag.20221255,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
Nearly Smooth Differential Operators on Surface Meshes}},

author = {
Mancinelli, Claudio
 and 
Puppo, Enrico
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221255}

}
@inproceedings{
10.2312:stag.20221257,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
Accurate Molecular Atom Selection in VR}},

author = {
Molina, Elena
 and 
Vázquez, Pere-Pau
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221257}

}
@inproceedings{
10.2312:stag.20221260,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
Optimizing Placements of 360° Panoramic Cameras in Indoor Environments by Integer Programming}},

author = {
Syu, Syuan-Rong
 and 
Peng, Chi-Han
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221260}

}
@inproceedings{
10.2312:stag.20221258,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
Enforcing Energy Preservation in Microfacet Models}},

author = {
Sforza, Davide
 and 
Pellacini, Fabio
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221258}

}
@inproceedings{
10.2312:stag.20221259,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
Versatile Geometric Flow Visualization by Controllable Shape and Volumetric Appearance}},

author = {
Zeidan, Mahmoud
 and 
Peters, Christoph
 and 
Rapp, Tobias
 and 
Dachsbacher, Carsten
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221259}

}
@inproceedings{
10.2312:stag.20221262,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
Deep Tracking for Robust Real-time Object Scanning}},

author = {
Lombardi, Marco
 and 
Savardi, Mattia
 and 
Signoroni, Alberto
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221262}

}
@inproceedings{
10.2312:stag.20221261,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
Creating Adaptive and Interactive Stories in Mixed Reality}},

author = {
Frau, Vittoria
 and 
Serra, Sergio
 and 
Spano, Lucio Davide
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221261}

}
@inproceedings{
10.2312:stag.20221264,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
Multiple Scattering Approximation for Real-time Underwater Spectral Rendering}},

author = {
Monzón, Néstor
 and 
Akkaynak, Derya
 and 
Gutiérrez, Diego
 and 
Muñoz, Adolfo
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221264}

}
@inproceedings{
10.2312:stag.20221263,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
Floor Plan Exploration Framework Based on Similarity Distances}},

author = {
Shih, Chia-Ying
 and 
Peng, Chi-Han
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221263}

}
@inproceedings{
10.2312:stag.20221267,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
SPIDER: SPherical Indoor DEpth Renderer}},

author = {
Tukur, Muhammad
 and 
Pintore, Giovanni
 and 
Gobbetti, Enrico
 and 
Schneider, Jens
 and 
Agus, Marco
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221267}

}
@inproceedings{
10.2312:stag.20221265,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
MUSE: Modeling Uncertainty as a Support for Environment}},

author = {
Miola, Marianna
 and 
Cabiddu, Daniela
 and 
Pittaluga, Simone
 and 
Vetuschi Zuccolini, Marino
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221265}

}
@inproceedings{
10.2312:stag.20221269,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
An Interactive Tuning Method for Generator Networks Trained by GAN}},

author = {
Zhou, Mengyuan
 and 
Yamaguchi, Yasushi
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221269}

}
@inproceedings{
10.2312:stag.20221268,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
CAD 3D Model Classification by Graph Neural Networks: A new Approach based on STEP Format}},

author = {
Mandelli, Lorenzo
 and 
Berretti, Stefano
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221268}

}
@inproceedings{
10.2312:stag.20221266,

booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference},

editor = {
Cabiddu, Daniela
 and 
Schneider, Teseo
 and 
Allegra, Dario
 and 
Catalano, Chiara Eva
 and 
Cherchi, Gianmarco
 and 
Scateni, Riccardo
},
title = {{
ProMED: Production Optimization for Additive Manufacturing of Medical Devices}},

author = {
Attene, Marco
 and 
Berti, Tiziano
 and 
Cabiddu, Daniela
 and 
Garosi, Antonio
 and 
Livesu, Marco
 and 
Pasztor, Zsolt
 and 
Petrovszki, Daniel
 and 
Ranieri, Andrea
},
year = {
2022},

publisher = {
The Eurographics Association},


ISSN = {2617-4855},
ISBN = {978-3-03868-191-5},

DOI = {
10.2312/stag.20221266}

}

Browse

Recent Submissions

Now showing 1 - 21 of 21
  • No Thumbnail Available
    Item
    Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference: Frontmatter
    (The Eurographics Association, 2022) Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
  • No Thumbnail Available
    Item
    A Graphical Framework to Study the Correlation between Geometric Design and Simulation
    (The Eurographics Association, 2022) Cabiddu, Daniela; Patané, Giuseppe; Spagnuolo, Michela; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    Partial differential equations can be solved on general polygonal and polyhedral meshes, through Polytopal Element Methods (PEMs). Unfortunately, the relation between geometry and analysis is still unknown and subject to ongoing research to identify weaker shape-regularity criteria under which PEMs can reliably work. We propose a graphical framework to support the analysis of the relation between the geometric properties of polygonal meshes and the numerical performances of PEM solvers. Our framework, namely PEMesh, allows the design of polygonal meshes that increasingly stress some geometric properties, by exploiting any external PEM solver, and supports the study of the correlation between the performances of such a solver and the geometric properties of the input mesh. Furthermore, it is highly modular, customisable, easy to use, and provides the possibility to export analysis results both as numerical values and graphical plots. The framework has a potential practical impact on ongoing and future research activities related to PEM methods, polygonal mesh generation and processing.
  • No Thumbnail Available
    Item
    A Computational Tool for the Analysis of 3D Bending-active Structures Based on the Dynamic Relaxation Method
    (The Eurographics Association, 2022) Manolas, Iason; Laccone, Francesco; Cherchi, Gianmarco; Malomo, Luigi; Cignoni, Paolo; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    The use of elastic deformation of straight or flat structural components for achieving complex 3D shapes has acquired attention from recent computational design works, particularly in architectural geometry. The so-called bending-active structures are built by deforming and restraining the components mutually to form a stable configuration. While the manufacturing of components from flat raw material and their assembly are simple and inexpensive, the complexity lies in the design phase, in which computational tools are required to predict the deformation and forces under a prescribed form-finding load or displacement. Currently, there is a scarcity of open and efficient tools that hinder the design of bending-active structures. This paper proposes and validates an open-source computational tool for predicting the static equilibrium of general bending-active structures in the form of a network of elements using the dynamic relaxation method. We apply our tool to various real-world examples and compare the results to a commercial FEM solver. The proposed tool shows accuracy and good time performance, making it a significant addition to the available open-source structural engineering toolkit.
  • No Thumbnail Available
    Item
    GIM3D: A 3D Dataset for Garment Segmentation
    (The Eurographics Association, 2022) Musoni, Pietro; Melzi, Simone; Castellani, Umberto; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    The 3D cloth segmentation task is particularly challenging due to the extreme variation of shapes, even among the same category of clothes. Several data-driven methods try to cope with this problem but they have to face the lack of available data capable to generalize to the variety of real-world data. For this reason, we present GIM3D (Garments In Motion 3D), a synthetic dataset of clothed 3D human characters in different poses. The over 4000 3D models in this dataset are produced by a physical simulation of clothes with different fabrics, sizes, and tightness, using animated human avatars having a large variety of shapes. Our dataset is composed of single meshes created to simulate 3D scans, with labels for the separate clothes and the visible body parts. We also provide an evaluation of the use of GIM3D as a training set on garment segmentation tasks using state-of-the-art data-driven methods for both meshes and point clouds.
  • No Thumbnail Available
    Item
    PC-GAU: PCA Basis of Scattered Gaussians for Shape Matching via Functional Maps
    (The Eurographics Association, 2022) Colombo, Michele; Boracchi, Giacomo; Melzi, Simone; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    Shape matching is a central problem in geometry processing applications, ranging from texture transfer to statistical shape analysis. The functional maps framework provides a compact representation of correspondences between discrete surfaces, which is then converted into point-wise maps required by real-world applications. The vast majority of methods based on functional maps involve the eigenfunctions of the Laplace-Beltrami Operator (LB) as the functional basis. A primary drawback of the LB basis is that its energy does not uniformly cover the surface. This fact gives rise to regions where the estimated correspondences are inaccurate, typically at tiny parts and protrusions. For this reason, state-of-the-art procedures to convert the functional maps (represented in the LB basis) into point-wise correspondences are often error-prone. We propose PCGAU, a new functional basis whose energy spreads on the whole shape more evenly than LB. As such, PC-GAU can replace the LB basis in existing shape matching pipelines. PC-GAU consists of the principal vectors obtained by applying Principal Component Analysis (PCA) to a dictionary of sparse Gaussian functions scattered on the surfaces. Through experimental evaluation of established benchmarks, we show that our basis produces more accurate point-wise maps —- compared to LB - when employed in the same shape-matching pipeline.
  • No Thumbnail Available
    Item
    Topological Initialization of Injective Integer Grid Maps
    (The Eurographics Association, 2022) Livesu, Marco; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    Integer Grid Maps (IGM) are a class of mappings characterized by integer isolines that align up to unit translations and rotations of multiples of 90 degrees. They are widely used in the context of remeshing, to lay a quadrilateral grid onto the mapped surface. Computing an IGM is notoriously a challenging task, because it requires to solve a numerical problem with mixed discrete and continuous variables which is known to be NP-Hard. As a result, state of the art methods rely on heuristics that may occasionally fail to produce a valid quadrilateral mesh. Existing pipelines incorporate a final sanitization step which attempts to fix such defects, but no guaranteees can be given in this regard. In this paper we propose a simple topological construction that allows to reduce the problem of computing an IGM to the one of mapping a topological disk to a convex domain. This is a much easier problem to deal with, because it does not endow integer translational and rotational constraints, permitting to obtain a parameterization that is guaranteed to incorporate all the correct integer transitions and to not contain degenerate or inverted elements. Despite provably correct, the so generated maps contain a considerable amount of geometric distortion and a poor quad connectivity, making this technique more suitable for a robust initialization rather than for the computation of an application-ready IGM. In the article we present the details of our construction, also analyzing its geometric and topological properties.
  • No Thumbnail Available
    Item
    Outside-in Priority-based Approximation of 3D Models in LEGO Bricks
    (The Eurographics Association, 2022) Fanni, Filippo Andrea; Rossi, Elisa De; Giachetti, Andrea; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    In this paper, we discuss the problem of converting a 3D mesh into an assembly of LEGO blocks. The major challenge of this task is how to aggregate the voxels derived by the shape discretization into a set of standard bricks guaranteeing global connectivity. We propose an outside-in priority-based heuristic method based on the analysis of the critical regions that are more likely to cause the creation of a legal assembly to fail. We show that our graph-building heuristic provides relevant advantages, making it easier to obtain a connected graph with good properties with respect to the layer-based or random aggregation strategies applied in most of the optimization approaches. We also propose BRICKS, a novel dataset for the evaluation of aggregation strategies. It includes voxelizations at 3 different resolutions of 33 shapes and allows the easy comparison of different voxel aggregation strategies independently of the shape discretization step and also considering their scalability. We use it to evaluate our approach with respect to graph-based connectivity measures, showing the advantages of the proposed strategy.
  • No Thumbnail Available
    Item
    Nearly Smooth Differential Operators on Surface Meshes
    (The Eurographics Association, 2022) Mancinelli, Claudio; Puppo, Enrico; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    Estimating the differential properties of a signal sampled on a surface is of paramount importance in many fields of applied sciences. In the common practice, the surface is discretized with a polygonal mesh, the signal is sampled at its vertices and extended linearly over the triangles. This means that the polyhedral metric is assumed over the surface; the first derivatives of the signal become discontinuous across edges; and the second derivatives vanish. We present a new method based on surface fitting, which efficiently estimates the metric tensor, and the first and second order Riemannian differential operators at any point on the surface. All our differential operators are smooth within each triangle and continuous across the edges, providing a much better estimate of differential quantities on the - yet unknown - underlying smooth manifold.
  • No Thumbnail Available
    Item
    Accurate Molecular Atom Selection in VR
    (The Eurographics Association, 2022) Molina, Elena; Vázquez, Pere-Pau; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    Target acquisition is a basic task that is part of almost any high-level interaction in 3D environments. Therefore, providing accurate selection is a necessity for most applications and games. When targets are small and scenes are cluttered, selection becomes inaccurate. This may lead to selecting the wrong elements which, apart from the time consumed, may become a frustrating experience. Besides the unintentional tremor, the button/trigger press for effectively selecting an element further reduces our stability, increasing the probability of an incorrect target acquisition. In this paper, we focus on molecular visualization and address the problem of selecting atoms, which are rendered as small spheres. We build upon previous progressive selection algorithms and present two alternatives that accelerate the selection of neighbors after an initial selection. We have implemented and analyzed such techniques through a formal user study and found that they were highly appreciated by the users. These selection methods may be suitable for other crowded environments beyond molecular visualization.
  • No Thumbnail Available
    Item
    Optimizing Placements of 360° Panoramic Cameras in Indoor Environments by Integer Programming
    (The Eurographics Association, 2022) Syu, Syuan-Rong; Peng, Chi-Han; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    We propose a computational approach to find a minimal set of 360° camera placements that together sufficiently cover an indoor environment for the building documentation problem in the architecture, engineering, and construction (AEC) industries. Our approach, based on a simple integer programming (IP) problem formulation, solves very efficiently and globally optimally. We conducted a study of using panoramas to capture the appearances of a real-world indoor environment, in which we found that our computed solutions are better than human solutions decided by both non-professional and professional users.
  • No Thumbnail Available
    Item
    Enforcing Energy Preservation in Microfacet Models
    (The Eurographics Association, 2022) Sforza, Davide; Pellacini, Fabio; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    Microfacet models suffer from a significant limitation: they only simulate a single interaction between light and surface, ignoring the subsequent scattering across the microfacets. As a consequence, the BSDF is not energy preserving, resulting in an unexpected darkening of rough specular surfaces. Energy compensation methods face this limitation by adding to the BSDF a secondary component accounting for multiple scattering contributions. While these methods are fast, robust and can be added to a renderer with relatively minor modifications, they involve the computation of the directional albedo. This quantity is expressed as an integral that does not have a closed-form solution, but it needs to be precomputed and stored in tables. These look-up tables are notoriously cumbersome to use, in particular on GPUs. This work obviates the need of look-up tables by fitting an analytic approximation of the directional albedo, which is a more practical solution. We propose a 2D rational polynomial of degree three to fit conductors and a 3D rational polynomial of degree three to fit dielectrics and materials composed of a specular layer on top of a diffuse one, such as plastics. We enforce energy preservation by rescaling the specular albedo, thus maintaining the same lobe shape. We validated our results via the furnace test, highlighting that materials rendered using our analytic approximations match almost exactly the behaviour of the ones rendered with the use of look-up tables, resulting in an energy-preserving model even at maximum roughness. The software we use to fit coefficients is open-source and can be used to fit other BSDF models as well.
  • No Thumbnail Available
    Item
    Versatile Geometric Flow Visualization by Controllable Shape and Volumetric Appearance
    (The Eurographics Association, 2022) Zeidan, Mahmoud; Peters, Christoph; Rapp, Tobias; Dachsbacher, Carsten; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    We present a novel visualization technique for geometry-based visualization of vector fields. Our approach generalizes and combines several existing approaches in a flexible framework using a scalable GPU-accelerated implementation. We map characteristic lines to a variety of glyphs. The user can define multiple cross-sectional shapes that will be used for extrusion. Our system interpolates between these shapes as requested, either based on attributes of the vector field and the characteristic lines or using global user-controlled parameters. Thus, a single characteristic line can use different cross-sectional shapes in different parts to aid the visualization of different phenomena. Transitions can be smooth or discrete and we support highlighting of silhouettes. Additionally, we track and visualize the rotation in the vector field and offer full control of the color mapping, the opacity and the radii along the characteristic lines. Texture-based approaches such as 3D line integral convolution (3D LIC) offer another avenue to vector field visualization. In 3D, they typically rely on sparsely placed seed points. We emulate their appearance with our geometry-based approach through an approximation of the volume integral within our glyphs. Combined with fast order-independent transparency, our GPU implementation achieves fast rendering, even at high resolutions, while keeping the memory footprint moderate.
  • No Thumbnail Available
    Item
    Deep Tracking for Robust Real-time Object Scanning
    (The Eurographics Association, 2022) Lombardi, Marco; Savardi, Mattia; Signoroni, Alberto; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    Nowadays, a high-fidelity 3d model representation can be obtained easily by means of handheld optical scanners, which offer a good level of reconstruction quality, portability, and low latency in scan-to-data. However, it is well known that the tracking process can be critical for such devices: sub-optimal lighting conditions, smooth surfaces in the scene, or occluded views and repetitive patterns are all sources of error. In this scenario, recent disruptive technologies such as sparse convolutional neural networks have been tailored to address common problems in 3D vision and analysis. Our work aims to integrate the most promising solutions into an operating framework which can then be used to achieve compelling results in 3D real-time reconstruction. Several scenes from a dataset containing dense views of objects are tested using our proposed pipeline and compared with the current state-of-the-art of online reconstruction.
  • No Thumbnail Available
    Item
    Creating Adaptive and Interactive Stories in Mixed Reality
    (The Eurographics Association, 2022) Frau, Vittoria; Serra, Sergio; Spano, Lucio Davide; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    The following paper proposes the study, the design and the preliminary development of a solution for supporting users without programming experience in creating stories in a Mixed Reality environment. We focus on a Mixed Reality interface split into two parts: the creation and observation phases. During the creation phase, the end user can build his/her own story in the immersive mode of the Mixed Reality experience. The user can also enjoy the stories that other users have designed by seeing the characters appear in their surrounding environment.
  • No Thumbnail Available
    Item
    Multiple Scattering Approximation for Real-time Underwater Spectral Rendering
    (The Eurographics Association, 2022) Monzón, Néstor; Akkaynak, Derya; Gutiérrez, Diego; Muñoz, Adolfo; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    We propose a physically-based, multispectral simulation to render underwater scenarios in real time, which also takes into account the RGB response curve of arbitrary sensors. Underwater illumination is mostly governed by multiple scattering, where light is scattered a number of times between particles before reaching the sensor. This phenomenon is therefore very low frequency and can be modeled as a function of depth and wavelength. Our approximation to multiple scattering is based on the measurable coefficient of diffuse downwelling attenuation. We show examples simulating underwater appearance under different scattering, absorption and downwelling coefficients of the Jerlov water types.
  • No Thumbnail Available
    Item
    Floor Plan Exploration Framework Based on Similarity Distances
    (The Eurographics Association, 2022) Shih, Chia-Ying; Peng, Chi-Han; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    Computational methods to compute similarities between floor plans can help architects explore floor plans in large datasets to avoid duplication of designs and to search for existing plans that satisfy their needs. Recently, LayoutGMN [PLF*21] delivered state-of-the-art performance for computing similarity scores between floor plans. However, the high computational costs of LayoutGMN make it unsuitable for the aforementioned applications. In this paper, we significantly reduced the times needed to query results computed by LayoutGMN by projecting the floor plans into a common low-dimensional (e.g., three) data space. The projection is done by optimizing for coordinates of floor plans with Euclidean distances mimicking their similarity scores originally calculated by LayoutGMN. Quantitative and qualitative evaluations show that our results match the distributions of the original LayoutGMN similarity scores. User study shows that our similarity results largely match human expectations.
  • No Thumbnail Available
    Item
    SPIDER: SPherical Indoor DEpth Renderer
    (The Eurographics Association, 2022) Tukur, Muhammad; Pintore, Giovanni; Gobbetti, Enrico; Schneider, Jens; Agus, Marco; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    Today's Extended Reality (XR) applications that call for specific Diminished Reality (DR) strategies to hide specific classes of objects are increasingly using 360? cameras, which can capture entire areas in a single picture. In this work, we present an interactive-based image editing and rendering system named SPIDER, that takes a spherical 360? indoor scene as input. The system incorporates the output of deep learning models to abstract the segmentation and depth images of full and empty rooms to allow users to perform interactive exploration and basic editing operations on the reconstructed indoor scene, namely: i) rendering of the scene in various modalities (point cloud, polygonal, wireframe) ii) refurnishing (transferring portions of rooms) iii) deferred shading through the usage of precomputed normal maps. These kinds of scene editing and manipulations can be used for assessing the inference from deep learning models and enable several Mixed Reality (XR) applications in areas such as furniture retails, interior designs, and real estates. Moreover, it can also be useful in data augmentation, arts, designs, and paintings.
  • No Thumbnail Available
    Item
    MUSE: Modeling Uncertainty as a Support for Environment
    (The Eurographics Association, 2022) Miola, Marianna; Cabiddu, Daniela; Pittaluga, Simone; Vetuschi Zuccolini, Marino; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    To fully understand a Natural System, the representation of an environmental variable's distribution in 3D space is a mandatory and complex task. The challenge derives from a scarcity of samples number in the survey domain (e.g., logs in a reservoir, soil samples, fixed acquisition sampling stations) or an implicit difficulty in the in-situ measurement of parameters. Field or lab measurements are generally considered error-free, although not so. That aspect, combined with conceptual and numerical approximations used to model phenomena, makes the results intrinsically less performing, fading the interpretation. In this context, we design a computational infrastructure to evaluate spatial uncertainty in a multi-scenario application in Environment survey and protection, such as in environmental geochemistry, coastal oceanography, or infrastructure engineering. Our Research aims to expand the operative knowledge by developing an open-source stochastic tool, named MUSE, the acronym for Modeling Uncertainty as a Support for Environment. At this stage, the methodology mainly includes the definition of a flexible environmental data format, a geometry processing module to discretize the space, and geostatistics tools to evaluate the spatial continuity of sampled parameters, predicting random variable distribution. The implementation of the uncertainty module and the development of a graphic interface for ad-hoc visualization will be integrated as the next step. The poster summarizes research purposes, and MUSE computational code structure developed so far.
  • No Thumbnail Available
    Item
    An Interactive Tuning Method for Generator Networks Trained by GAN
    (The Eurographics Association, 2022) Zhou, Mengyuan; Yamaguchi, Yasushi; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    The recent studies on GAN achieved impressive results in image synthesis. However, they are still not so perfect that output images may contain unnatural regions. We propose a tuning method for generator networks trained by GAN to improve their results by interactively removing unexpected objects and textures or changing the object colors. Our method could find and ablate those units in the generator networks that are highly related to the specific regions or their colors. Compared to the related studies, our proposed method can tune pre-trained generator networks without relying on any additional information like segmentation-based networks. We built the interactive system based on our method, capable of tuning the generator networks to make the resulting images as expected. The experiments show that our method could remove only unexpected objects and textures. It could change the selected area color as well. The method also gives us some hints to discuss the properties of generator networks which layers and units are associated with objects, textures, or colors.
  • No Thumbnail Available
    Item
    CAD 3D Model Classification by Graph Neural Networks: A new Approach based on STEP Format
    (The Eurographics Association, 2022) Mandelli, Lorenzo; Berretti, Stefano; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    In this paper, we introduce a new approach for retrieval and classification of 3D models that directly performs in the Computer- Aided Design (CAD) format without any conversion to other representations like point clouds or meshes, thus avoiding any loss of information. Among the various CAD formats, we consider the widely used STEP extension, which represents a standard for product manufacturing information. This particular format represents a 3D model as a set of primitive elements such as surfaces and vertices linked together. In our approach, we exploit the linked structure of STEP files to create a graph in which the nodes are the primitive elements and the arcs are the connections between them. We then use Graph Neural Networks (GNNs) to solve the problem of model classification. Finally, we created two datasets of 3D models in native CAD format, respectively, by collecting data from the Traceparts model library and from the Configurators software modeling company. We used these datasets to test and compare our approach with respect to state-of-the-art methods that consider other 3D formats. Our code is available at https://github.com/divanoLetto/3D_STEP_Classification
  • No Thumbnail Available
    Item
    ProMED: Production Optimization for Additive Manufacturing of Medical Devices
    (The Eurographics Association, 2022) Attene, Marco; Berti, Tiziano; Cabiddu, Daniela; Garosi, Antonio; Livesu, Marco; Pasztor, Zsolt; Petrovszki, Daniel; Ranieri, Andrea; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    In metal 3D printing, and in particular in the production of dental implants and prosthodontics, a careful geometric analysis of the parts is key to maximize the overall throughput and minimize fabrication costs. Herewith we describe the main results obtained within the European Project DIGITBrain/ProMED, whose objective is to optimize the production of customized metal medical devices. ProMED delivers a digital twin of an existing production pipeline and allows for the quick simulation of a large number of fabrication scenarios. This is achieved thanks to a clever geometric analysis driving the optimal orientation of the part in the platform combined with a geometry-based process simulator that makes it possible to estimate fabrication time, material consumption, human labour, and other useful information that greatly supports users in the task of optimizing the overall fabrication performances from many meaningful points of view. Compared to standard simulation software provided by printer vendors, our approach can be orders of magnitude faster: this makes it possible to analyze and compare a great number of scenarios to support companies in their day-by-day decisions for real productions.