11 results
Search Results
Now showing 1 - 10 of 11
Item An Approach to the Decomposition of Solids with Voids via Morse Theory(The Eurographics Association, 2023) Pareja-Corcho, Juan; Montoya-Zapata, Diego; Moreno, Aitor; Cadavid, Carlos; Posada, Jorge; Arenas-Tobon, Ketzare; Ruiz-Salguero, Oscar; Banterle, Francesco; Caggianese, Giuseppe; Capece, Nicola; Erra, Ugo; Lupinetti, Katia; Manfredi, GildaThe decomposition of solids is a problem of interest in areas of engineering such as feature recognition or manufacturing planning. The problem can be stated as finding a set of smaller and simpler pieces that glued together amount to the initial solid. This decomposition can be guided by geometrical or topological criteria and be applied to either surfaces or solids (embedded manifolds). Most topological decompositions rely on Morse theory to identify changes in the topology of a manifold. A Morse function f is defined on the manifold and the manifold's topology is studied by studying the behaviour of the critical points of f . A popular structure used to encode this behaviour is the Reeb graph. Reeb graph-based decompositions have proven to work well for surfaces and for solids without inner voids, but fail to consider solids with inner voids. In this work we present a methodology based on the handle-decomposition of a manifold that can encode changes in the topology of solids both with and without inner voids. Our methodology uses the Boundary Representation of the solid and a shape similarity criteria to identify changes in the topology of both the outer and inner boundary(ies) of the solid. Our methodology is defined for Morse functions that produce parallel planar level sets and we do not consider the case of annidated solids (i.e. solids within other solids). We present an algorithm to implement our methodology and execute experiments on several datasets. Future work includes the testing of the methodology with functions different to the height function and the speed up of the algorithm's data structure.Item Spectral-based Segmentation for Functional Shape-matching(The Eurographics Association, 2023) Mancinelli, Claudio; Melzi, Simone; Banterle, Francesco; Caggianese, Giuseppe; Capece, Nicola; Erra, Ugo; Lupinetti, Katia; Manfredi, GildaIn Computer Graphics and Computer Vision, shape co-segmentation and shape-matching are fundamental tasks with diverse applications, from statistical shape analysis to human-robot interaction. These problems respectively target establishing segmentto- segment and point-to-point correspondences between shapes, which are crucial task for numerous practical scenarios. Notably, co-segmentation can aid in point-wise correspondence estimation in shape-matching pipelines like the functional maps framework. Our paper introduces an innovative shape segmentation pipeline which provides coherent segmentation for shapes within the same class. Through comprehensive evaluation on a diverse test set comprising shapes from various datasets and classes, we demonstrate the coherence of our segmentation approach. Moreover, our method significantly improves accuracy in shape matching scenarios, as evidenced by comparisons with the original functional maps approach. Importantly, these enhancements come with minimal computational overhead. Our work not only introduces a novel coherent segmentation method and a valuable tool for improving correspondence accuracy within functional maps, but also contributes to the theoretical foundations of this impactful field, inspiring further research.Item Localized Gaussians as Self-Attention Weights for Point Clouds Correspondence(The Eurographics Association, 2024) Riva, Alessandro; Raganato, Alessandro; Melzi, Simone; Caputo, Ariel; Garro, Valeria; Giachetti, Andrea; Castellani, Umberto; Dulecha, Tinsae GebrechristosCurrent data-driven methodologies for point cloud matching demand extensive training time and computational resources, presenting significant challenges for model deployment and application. In the point cloud matching task, recent advancements with an encoder-only Transformer architecture have revealed the emergence of semantically meaningful patterns in the attention heads, particularly resembling Gaussian functions centered on each point of the input shape. In this work, we further investigate this phenomenon by integrating these patterns as fixed attention weights within the attention heads of the Transformer architecture. We evaluate two variants: one utilizing predetermined variance values for the Gaussians, and another where the variance values are treated as learnable parameters. Additionally we analyze the performances on noisy data and explore a possible way to improve robustness to noise. Our findings demonstrate that fixing the attention weights not only accelerates the training process but also enhances the stability of the optimization. Furthermore, we conducted an ablation study to identify the specific layers where the infused information is most impactful and to understand the reliance of the network on this information.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, RuggeroThe 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%.Item Semantic Segmentation of High-resolution Point Clouds Representing Urban Contexts(The Eurographics Association, 2023) Romanengo, Chiara; Cabiddu, Daniela; Pittaluga, Simone; Mortara, Michela; Banterle, Francesco; Caggianese, Giuseppe; Capece, Nicola; Erra, Ugo; Lupinetti, Katia; Manfredi, GildaPoint clouds are becoming an increasingly common digital representation of real-world objects, and they are particularly efficient when dealing with large-scale objects and/or when extremely high-resolution is required. The focus of our work is on the analysis, 3D feature extraction and semantic annotation of point clouds representing urban scenes, coming from various acquisition technologies, e.g., terrestrial (fixed or mobile) or aerial laser scanning or photogrammetry; the task is challenging, due to data dimensionality and noise. In particular, we present a pipeline to segment high-resolution point clouds representing urban environments into geometric primitives; we focus on planes, cylinders and spheres, which are the main features of buildings (walls, roofs, arches, ...) and ground surfaces (streets, pavements, platforms), and identify the unique parameters of each instance. This paper focuses on the semantic segmentation of buildings, but the approach is currently being generalised to manage extended urban areas. Given a dense point cloud representing a specific building, we firstly apply a binary space partitioning method to obtain small enough sub-clouds that can be processed. Then, a combination of the well-known RANSAC algorithm and a recognition method based on the Hough transform (HT) is applied to each sub-cloud to obtain a semantic segmentation into salient elements, like façades, walls and roofs. The parameters of primitive instances are saved as metadata to document the structural element of buildings for further thematic analyses, e.g., energy efficiency. We present a case study on the city of Catania, Italy, where two buildings of historical and artistic value have been digitized at very high resolution. Our approach is able to semantically segment these huge point clouds and it proves robust to uneven sampling density, input noise and outliers.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, RiccardoThe 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.Item Mesh Comparison Using Regular Grids(The Eurographics Association, 2024) Kaye, Patrizia; Ivrissimtzis, Ioannis; Caputo, Ariel; Garro, Valeria; Giachetti, Andrea; Castellani, Umberto; Dulecha, Tinsae GebrechristosA symmetric grid-based approach to mesh comparison is proposed, providing intuitive visual results alongside an objective measure of the local differences between meshes. The difference function is defined on the nodes of a regular 3D lattice, making it suitable as input for a variety of analysis algorithms. The visual results are compared and comparable to the Metro tool.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, RiccardoShape 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.Item Reposing and Retargeting Unrigged Characters with Intrinsic-extrinsic Transfer(The Eurographics Association, 2021) Musoni, Pietro; Marin, Riccardo; Melzi, Simone; Castellani, Umberto; Frosini, Patrizio and Giorgi, Daniela and Melzi, Simone and Rodolà , EmanueleIn the 3D digital world, deformations and animations of shapes are fundamental topics for several applications. The entertainment industry, virtual and augmented reality, human-robot interactions are just some examples that pay attention to animation processes and related tools. In these contexts, researchers from several communities desire to govern deformations and animations of 3D geometries. This task is generally very complicated because it requires several skills covering different kinds of knowledge. For this reason, we propose a ready-to-use procedure to transfer a given animation from a source shape to a target shape that shares the same global structure. Our method proposes highly geometrical transferring, reposing, and retargeting, providing high-quality and efficient transfer, as shown in the qualitative evaluation that we report in the experimental section. The animation transfer we provide will potentially impact different scenarios, such as data augmentation for learning-based procedures or virtual avatar generation for orthopedic rehabilitation and social applications.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, StefanoWe 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.