One of the primary challenges inherent in utilizing deep learning models is the scarcity and accessibility hurdles associated with acquiring datasets of sufficient size to facilitate effective training of these networks. This is particularly significant in object detection, shape completion, and fracture assembly. Instead of scanning a large number of real-world fragments, it is possible to generate massive datasets with synthetic pieces. However, realistic fragmentation is computationally intensive in the preparation (e.g., pre-factured models) and generation. Otherwise, simpler algorithms such as Voronoi diagrams provide faster processing speeds at the expense of compromising realism. In this context, it is required to balance computational efficiency and realism. This paper introduces a GPU-based framework for the massive generation of voxelized fragments derived from high-resolution 3D models, specifically prepared for their utilization as training sets for machine learning models. This rapid pipeline enables controlling how many pieces are produced, their dispersion and the appearance of subtle effects such as erosion. We have tested our pipeline with an archaeological dataset, producing more than 1M fragmented pieces from 1,052 Iberian vessels ( Github ). Although this work primarily intends to provide pieces as implicit data represented by voxels, triangle meshes and point clouds can also be inferred from the initial implicit representation. To underscore the unparalleled benefits of CPU and GPU acceleration in generating vast datasets, we compared against a realistic fragment generator that highlights the potential of our approach, both in terms of applicability and processing time. We also demonstrate the synergies between our pipeline and realistic simulators, which frequently cannot select the number and size of resulting pieces. To this end, a deep learning model was trained over realistic fragments and our dataset, showing similar results. • GPU-based fragmentation of voxelized artefacts for simulating brittle fractures. • Generation of large datasets for training machine learning models. • Definition of how many fragments are produced, their dispersion and appearance. • Publication of a dataset comprising more than 1M fragments.

Accurate completion of archaeological artifacts is a critical aspect in several archaeological studies, including documentation of variations in style, inference of chronological and ethnic groups, and trading routes trends, among many others. However, most available pottery is fragmented, leading to missing textural and morphological cues. Currently, the reassembly and completion of fragmented ceramics is a daunting and time-consuming task, done almost exclusively by hand, which requires the physical manipulation of the fragments. To overcome the challenges of manual reconstruction, reduce the materials' exposure and deterioration, and improve the quality of reconstructed samples, we present IberianVoxel, a novel 3D Autoencoder Generative Adversarial Network (3D AE-GAN) framework tested on an extensive database with complete and fragmented references. We generated a collection of 1001 3D voxelized samples and their fragmented references from Iberian wheel-made pottery profiles. The fragments generated are stratified into different size groups and across multiple pottery classes. Lastly, we provide quantitative and qualitative assessments to measure the quality of the reconstructed voxelized samples by our proposed method and archaeologists' evaluation.

Computers are extensively used for training and simulating tasks that are hazardous in a real-life situation or require expensive, delicate or difficult to access equipment. In the present work we describe a system for the assessment of clinical practices involving the use of electrotherapy. The existing variety of currents, electrical parameters and electrode configurations make this a challenging subject for undergraduate physical therapy students. Extensive training is required before they can treat real patients, since an incorrect practice may have no effect on the patient’s condition, or even worse, cause severe pain or burns. Our system, implemented as a serious game, can facilitate this training, since the opportunity for supervised clinical practice with real equipment is limited. Our goal was to mimic the assessment of an electrotherapy treatment by an expert, by evaluating each of its aspects in a flexible way, detecting and highlighting critical situations that can affect the patient’s integrity and computing an overall score for the whole treatment. For this purpose, we have modeled the valid values of each electrical parameter (frequency, pulse width, intensity, etc.) and the treatment time using fuzzy sets. We also characterize the placement of the electrodes in the area of treatment through three geometric quantities (orientation, distance to center and spacing) on which three fuzzy terms are defined (well oriented, centered and well distributed). For each of these variables we get partial scores that are finally aggregated into an overall treatment score through a pessimistic exponential ordered weighted average operation. In order to test the reliability of the system we conducted an experiment with a group of physical therapy students that revealed a substantial agreement with a human expert.

The widespread use of LiDAR technology in a multitude of domains has produced a growing availability of massive high-resolution point datasets that demand new approaches for efficient organization and storage, filtering using different spatio-temporal criteria, selective/progressive visualization, processing and analysis, and collaborative editing. Ideally, LiDAR data coming from multiple sources and organized in different datasets should be accessible in a simple, uniform, and ubiquitous way to comply with the FAIR principle proposed by the Open Geospatial Consortium: Findable, Accessible, Interoperable, and Reusable. With this goal in mind, we present SPSLiDAR, a conceptual model with a simple interface for repositories of LiDAR data that can be adapted to the needs of different applications. SPSLiDAR includes aspects, such as the arrangement of related datasets into workspaces on a world scale, support for overlapping datasets with different resolutions or acquired at different times, and hierarchical organization of point data, enabling levels of detail and selective download. We also describe in detail an implementation of this model aimed at visualization and downloading of large datasets using the MongoDB database. Finally, we show some experimental results of this implementation using real data, such as its space requirements, upload latency, access latency, and throughput.

Time series analysis has been an active area of research for years, with important applications in forecasting or discovery of hidden information such as patterns or anomalies in observed data. In recent years, the use of time series analysis techniques for the generation of descriptions and summaries in natural language of any variable, such as temperature, heart rate or CO2 emission has received increasing attention. Natural language has been recognized as more effective than traditional graphical representations of numerical data in many cases, in particular in situations where a large amount of data needs to be inspected or when the user lacks the necessary background and skills to interpret it. In this work, we describe a novel mechanism to generate linguistic descriptions of time series using natural language and fuzzy logic techniques. The proposed method generates quality summaries capturing the time series features that are relevant for a user in a particular application, and can be easily customized for different domains. This approach has been successfully applied to the generation of linguistic descriptions of bed restlessness data from residents at TigerPlace (Columbia, Missouri), which is used as a case study to illustrate the modeling process and show the quality of the descriptions obtained.

We introduce QuadStack, a novel algorithm for volumetric data compression and direct rendering. Our algorithm exploits the data redundancy often found in layered datasets which are common in science and engineering fields such as geology, biology, mechanical engineering, medicine, etc. QuadStack first compresses the volumetric data into vertical stacks which are then compressed into a quadtree that identifies and represents the layered structures at the internal nodes. The associated data (color, material, density, etc.) and shape of these layer structures are decoupled and encoded independently, leading to high compression rates (4× to 54× of the original voxel model memory footprint in our experiments). We also introduce an algorithm for value retrieving from the QuadStack representation and we show that the access has logarithmic complexity. Because of the fast access, QuadStack is suitable for efficient data representation and direct rendering. We show that our GPU implementation performs comparably in speed with the state-of-the-art algorithms (18-79 MRays/s in our implementation), while maintaining a significantly smaller memory footprint.

This paper presents a formal framework for the representation of three-dimensional geospatial data and the definition of common geographic information system (GIS) spatial operations. We use the compact stack-based representation of terrains (SBRT) in order to model geological volumetric data, both at the surface and subsurface levels, thus preventing the large storage requirements of regular voxel models. The main contribution of this paper is fitting the SBRT into the geo-atom theory in a seamless way, providing it with a sound formal geographic foundation. In addition we have defined a set of common spatial operations on this representation using the tools provided by map algebra. More complex geoprocessing operations or geophysical simulations using the SBRT as representation can be implemented as a composition of these fundamental operations. Finally a data model and an implementation extending the coverage concept provided by the Geography Markup Language standard are suggested. Geoscientists and GIS professionals can take advantage of this model to exchange and reuse geoinformation within a well-specified framework.

Abstract The generation of a stereoscopic animation film requires doubling the rendering times and hence the cost. In this paper, we address this problem and propose an automatic system for generating a stereo pair from a given image and its depth map. Although several solutions exist in the literature, the high standards of image quality required in the context of a professional animation studio forced us to develop specially crafted algorithms that avoid artefacts caused by occlusions, anti‐aliasing filters, etc. This paper describes all the algorithms involved in our system and provides their GPU implementation. The proposed system has been tested with real‐life working scenarios. Our experiments show that the second view of the stereoscopic pair can be computed with as little as 15% of the effort of the original image while guaranteeing a similar quality.

This work describes the EL-REP, a new 2D decomposition scheme with interesting properties and applications. The EL-REP can be computed for one or more simple polygons of any kind: convex or nonconvex, with or without holes and even with several shells. A method for constructing this decomposition is described in detail, together with several of its main applications: fast point-in-polygon inclusion test, 2D location, triangulation of polygons, and collision detection.