Sistema integrado de generación de mapas de profundidad para videoconferencia 3D en tiempo real

This paper presents the implementation of a high quality real-time 3D video system intended for 3D videoconferencing -- Basically, the system is able to extract depth information from a pair of images coming from a short-baseline camera setup -- The system is based on the use of a variant of the adaptive support-weight algorithm to be applied on GPU-based architectures -- The reason to do it is to get real-time results without compromising accuracy and also to reduce costs by using commodity hardware -- The complete system runs over the GStreamer multimedia software platform to make it even more flexible -- Moreover, an autoestereoscopic display has been used as the end-up terminal for 3D content visualization

Interfaz AIS para aplicaciones en CAD/CAM/CG

Los modeladores geométricos más comunes en el mercado ofrecen, además de sus servicios de modelado, una API (Application Programming Interface) que permite la construcción de aplicaciones o software cliente -- Estas aplicaciones aprovechan los servicios básicos del modelador para proveer tareas específicas -- Sin embargo las diferencias entre API´s de distintos modeladores imposibilita el intercambio del software cliente entre ellos -- Application Interface Specification -AIS- es una API genérica para ser usada por aplicaciones cliente de los modeladores geométricos -- Este artículo reporta la implementación de AIS sobre AutoCAD® y MicroStation® y discute aspectos importantes de dicha implementación -- Además presenta una aplicación cliente neutra que habla lenguaje AIS y por lo tanto se ejecuta transparentemente sobre los dos modeladores -- AIS se presenta como una alternativa económica para escribir aplicaciones de CAD/CAM/CG -- Futuros desarrollos incluyen la implementación de AIS para labores gráficas y/o de base de datos

Trabajos 3D Realizados en la Puerta 1 del Complejo Arqueológico de Perdigoes (Portugal): estado de la cuestión

La Universidad de Málaga lleva excavando en un proyecto internacional desde 2008 en el Complejo Arqueológico de Perdigões. La incorporación de las tecnologías 3D a la arqueología es hoy en día un hecho y en este proyecto no ha sido menos. El presente artículo tiene como objetivo presentar los trabajos realizados en el Complejo Arqueológico de Perdigoes en lo que se refiere al uso de técnologías 3D.

Reconstituição histórica virtual do retábulo-mor da Igreja do Espírito Santo de Évora: aplicação ao Património da infografia web-based

As a part of a multidisciplinary and integrated research, including conservation sciences and history, a proposal is presented for the historical reconstitution and the virtual restoration of the mannerist altarpiece of the main altar at the Espírito Santo Church, in Évora. The collected data is abundant and the scientific information, because of its technicality, is less prone to be easily understood by the general public, thus becoming less accessible. Web-based infographics are explored as privileged forms of disseminating results and raising awareness to Cultural Heritage. The project materializes as an Internet platform where data and a reconstitution proposal are shared in a visual and interactive way. In addition to the digital virtual reconstitution (2D), some tridimensional models (3D) are presented of various elements of the altarpiece, obtained using methods of computer graphics and digital photogrammetry

Analysis of the main phenomena affecting solid rocket motors internal ballistics

In solid rocket motors, the absence of combustion controllability and the large amount of financial resources involved in full-scale firing tests, increase the importance of numerical simulations in order to asses stringent mission thrust requirements and evaluate the influence of thrust chamber phenomena affecting the grain combustion. Among those phenomena, grain local defects (propellant casting inclusions and debondings), combustion heat accumulation involving pressure peaks (Friedman Curl effect), and case-insulating thermal protection material ablation affect thrust prediction in terms of not negligible deviations with respect to the nominal expected trace. Most of the recent models have proposed a simplified treatment to the problem using empirical corrective functions, with the disadvantages of not fully understanding the physical dynamics and thus of not obtaining predictive results for different configurations of solid rocket motors in a boundary conditions-varied scenario. This work is aimed to introduce different mathematical approaches to model, analyze, and predict the abovementioned phenomena, presenting a detailed physical interpretation based on existing SRMs configurations. Internal ballistics predictions are obtained with an in-house simulation software, where the adoption of a dynamic three-dimensional triangular mesh together with advanced computer graphics methods, allows the previous target to be reached. Numerical procedures are explained in detail. Simulation results are carried out and discussed based on experimental data.

Exploring domain-informed and physics-guided learning in image-to-image translation

Image-to-image (i2i) translation networks can generate fake images beneficial for many applications in augmented reality, computer graphics, and robotics. However, they require large scale datasets and high contextual understanding to be trained correctly. In this thesis, we propose strategies for solving these problems, improving performances of i2i translation networks by using domain- or physics-related priors. The thesis is divided into two parts. In Part I, we exploit human abstraction capabilities to identify existing relationships in images, thus defining domains that can be leveraged to improve data usage efficiency. We use additional domain-related information to train networks on web-crawled data, hallucinate scenarios unseen during training, and perform few-shot learning. In Part II, we instead rely on physics priors. First, we combine realistic physics-based rendering with generative networks to boost outputs realism and controllability. Then, we exploit naive physical guidance to drive a manifold reorganization, which allowed generating continuous conditions such as timelapses.

Geometric Deep Learning per il denoising di mesh 3D

La crescente disponibilità di scanner 3D ha reso più semplice l’acquisizione di modelli 3D dall’ambiente. A causa delle inevitabili imperfezioni ed errori che possono avvenire durante la fase di scansione, i modelli acquisiti possono risultare a volte inutilizzabili ed affetti da rumore. Le tecniche di denoising hanno come obiettivo quello di rimuovere dalla superficie della mesh 3D scannerizzata i disturbi provocati dal rumore, ristabilendo le caratteristiche originali della superficie senza introdurre false informazioni. Per risolvere questo problema, un approccio innovativo è quello di utilizzare il Geometric Deep Learning per addestrare una Rete Neurale in maniera da renderla in grado di eseguire efficacemente il denoising di mesh. L’obiettivo di questa tesi è descrivere il Geometric Deep Learning nell’ambito del problema sotto esame.

Modellazione grafica di elicotteri per la simulazione del volo

L'obiettivo di questo elaborato di tesi è la modellazione grafica delle cabine di pilotaggio di due elicotteri civili: si prevede una futura implementazione del modello di volo completo sul simulatore FlightGear. I due velivoli presi in considerazione sono stati sviluppati dall'azienda AgustaWestland e sono denominati AW109 e AW139. I modelli di volo sono composti da una parte grafica e dal modello dinamico del volo. La presente tesi si occupa del primo aspetto. Il lavoro di tesi è iniziato con una fase preliminare di ricerca che ha richiesto lo studio di come i modelli dinamici di volo siano implementati nel simulatore FlightGear; è stato, inoltre, approfondito l'utilizzo del linguaggio di markup XML necessario a descrivere il funzionamento e le caratteristiche dei velivoli in FlightGear. Ha fatto seguito la fase di scrittura dei file XML, facendo riferimento a modelli di elicotteri preesistenti e all'effettiva modellazione degli strumenti di bordo, attraverso il programma CAD Blender. Nella fase finale sono stati studiati e posizionati i vari strumenti principali di bordo, consultando i manuali degli elicotteri e ottenendo delle cabine di pilotaggio del tutto simili a quelle reali dei velivoli considerati. Gli sviluppi futuri di questo lavoro prevedono l'integrazione dei modelli grafici qui implementati nel modello di volo completo dei due elicotteri presi in considerazione.

Mitigating non-Lambertian surfaces issues in Stereo Matching with Neural Radiance Fields

Depth estimation from images has long been regarded as a preferable alternative compared to expensive and intrusive active sensors, such as LiDAR and ToF. The topic has attracted the attention of an increasingly wide audience thanks to the great amount of application domains, such as autonomous driving, robotic navigation and 3D reconstruction. Among the various techniques employed for depth estimation, stereo matching is one of the most widespread, owing to its robustness, speed and simplicity in setup. Recent developments has been aided by the abundance of annotated stereo images, which granted to deep learning the opportunity to thrive in a research area where deep networks can reach state-of-the-art sub-pixel precision in most cases. Despite the recent findings, stereo matching still begets many open challenges, two among them being finding pixel correspondences in presence of objects that exhibits a non-Lambertian behaviour and processing high-resolution images. Recently, a novel dataset named Booster, which contains high-resolution stereo pairs featuring a large collection of labeled non-Lambertian objects, has been released. The work shown that training state-of-the-art deep neural network on such data improves the generalization capabilities of these networks also in presence of non-Lambertian surfaces. Regardless being a further step to tackle the aforementioned challenge, Booster includes a rather small number of annotated images, and thus cannot satisfy the intensive training requirements of deep learning. This thesis work aims to investigate novel view synthesis techniques to augment the Booster dataset, with ultimate goal of improving stereo matching reliability in presence of high-resolution images that displays non-Lambertian surfaces.

Impossible Space circolare per favorire la locomozione naturale

In questa relazione di tesi verrà affrontato il problema della locomozione naturale in ambienti virtuali che possiedono una grandezza maggiore dello spazio reale nel quale l'utente si muove. Negli anni sono stati sviluppati numerosi metodi di navigazione, ma tra tutti la locomozione naturale è il sistema che porta un livello di immersione maggiore nello spazio virtuale, più di qualsiasi altra tecnica. In questo lavoro di tesi verrà proposto un algoritmo in grado di favorire la locomozione naturale all'interno di lunghi spazi chiusi, andando a modificare la geometria dello spazio virtuale (che andrà ad assumere una forma circolare) e mantendendo comunque un certo grado di realismo dal punto di vista dell'utente. L'obiettivo è quello di tradurre uno spazio virtuale chiuso e lungo (caso comune: un corridoio) in una forma circolare inscritta in una stanza di 2x2m, con un approccio simile a quello degli impossible spaces, con l'obiettivo di studiare in futuro entro quale percentuale di sovrapposizione l'utente si accorge di trovarsi in una geometria impossibile. Nel primo capitolo verranno introdotti i concetti chiave di VR e AR, nonché un'introduzione all'Engine Unity e al software Blender. Nel secondo capitolo si tratterà di computer graphics, quindi si introdurranno i concetti base della grafica 3D con un focus sulla matematica alla base di ogni processo grafico. Nel terzo capitolo verrà affrontano il concetto di embodiment, quindi la percezione del proprio corpo, l'importanza dell'immersitvità dei sistemi virtuali e verrà descritto un paper precedentemente realizzato riguardante tale concetto. Nel capitolo quattro si parlerà del movimento all'interno dei sistemi di realtà virtuale, della locomozione naturale e delle tecniche per rendere tale metodo più accessibile. Nel capitolo cinque infine verrà descritto l'algoritmo realizzato e verranno mostrati i risultati.

Neural Radiance Fields for Relighting and View Synthesis

Neural scene representation and neural rendering are new computer vision techniques that enable the reconstruction and implicit representation of real 3D scenes from a set of 2D captured images, by fitting a deep neural network. The trained network can then be used to render novel views of the scene. A recent work in this field, Neural Radiance Fields (NeRF), presented a state-of-the-art approach, which uses a simple Multilayer Perceptron (MLP) to generate photo-realistic RGB images of a scene from arbitrary viewpoints. However, NeRF does not model any light interaction with the fitted scene; therefore, despite producing compelling results for the view synthesis task, it does not provide a solution for relighting. In this work, we propose a new architecture to enable relighting capabilities in NeRF-based representations and we introduce a new real-world dataset to train and evaluate such a model. Our method demonstrates the ability to perform realistic rendering of novel views under arbitrary lighting conditions.

Parallel Computer Vision Algorithms for Graphics Processing Units

La evolución de los teléfonos móviles inteligentes, dotados de cámaras digitales, está provocando una creciente demanda de aplicaciones cada vez más complejas que necesitan algoritmos de visión artificial en tiempo real; puesto que el tamaño de las señales de vídeo no hace sino aumentar y en cambio el rendimiento de los procesadores de un solo núcleo se ha estancado, los nuevos algoritmos que se diseñen para visión artificial han de ser paralelos para poder ejecutarse en múltiples procesadores y ser computacionalmente escalables. Una de las clases de procesadores más interesantes en la actualidad se encuentra en las tarjetas gráficas (GPU), que son dispositivos que ofrecen un alto grado de paralelismo, un excelente rendimiento numérico y una creciente versatilidad, lo que los hace interesantes para llevar a cabo computación científica. En esta tesis se exploran dos aplicaciones de visión artificial que revisten una gran complejidad computacional y no pueden ser ejecutadas en tiempo real empleando procesadores tradicionales. En cambio, como se demuestra en esta tesis, la paralelización de las distintas subtareas y su implementación sobre una GPU arrojan los resultados deseados de ejecución con tasas de refresco interactivas. Asimismo, se propone una técnica para la evaluación rápida de funciones de complejidad arbitraria especialmente indicada para su uso en una GPU. En primer lugar se estudia la aplicación de técnicas de síntesis de imágenes virtuales a partir de únicamente dos cámaras lejanas y no paralelas—en contraste con la configuración habitual en TV 3D de cámaras cercanas y paralelas—con información de color y profundidad. Empleando filtros de mediana modificados para la elaboración de un mapa de profundidad virtual y proyecciones inversas, se comprueba que estas técnicas son adecuadas para una libre elección del punto de vista. Además, se demuestra que la codificación de la información de profundidad con respecto a un sistema de referencia global es sumamente perjudicial y debería ser evitada. Por otro lado se propone un sistema de detección de objetos móviles basado en técnicas de estimación de densidad con funciones locales. Este tipo de técnicas es muy adecuada para el modelado de escenas complejas con fondos multimodales, pero ha recibido poco uso debido a su gran complejidad computacional. El sistema propuesto, implementado en tiempo real sobre una GPU, incluye propuestas para la estimación dinámica de los anchos de banda de las funciones locales, actualización selectiva del modelo de fondo, actualización de la posición de las muestras de referencia del modelo de primer plano empleando un filtro de partículas multirregión y selección automática de regiones de interés para reducir el coste computacional. Los resultados, evaluados sobre diversas bases de datos y comparados con otros algoritmos del estado del arte, demuestran la gran versatilidad y calidad de la propuesta. Finalmente se propone un método para la aproximación de funciones arbitrarias empleando funciones continuas lineales a tramos, especialmente indicada para su implementación en una GPU mediante el uso de las unidades de filtraje de texturas, normalmente no utilizadas para cómputo numérico. La propuesta incluye un riguroso análisis matemático del error cometido en la aproximación en función del número de muestras empleadas, así como un método para la obtención de una partición cuasióptima del dominio de la función para minimizar el error. ABSTRACT The evolution of smartphones, all equipped with digital cameras, is driving a growing demand for ever more complex applications that need to rely on real-time computer vision algorithms. However, video signals are only increasing in size, whereas the performance of single-core processors has somewhat stagnated in the past few years. Consequently, new computer vision algorithms will need to be parallel to run on multiple processors and be computationally scalable. One of the most promising classes of processors nowadays can be found in graphics processing units (GPU). These are devices offering a high parallelism degree, excellent numerical performance and increasing versatility, which makes them interesting to run scientific computations. In this thesis, we explore two computer vision applications with a high computational complexity that precludes them from running in real time on traditional uniprocessors. However, we show that by parallelizing subtasks and implementing them on a GPU, both applications attain their goals of running at interactive frame rates. In addition, we propose a technique for fast evaluation of arbitrarily complex functions, specially designed for GPU implementation. First, we explore the application of depth-image–based rendering techniques to the unusual configuration of two convergent, wide baseline cameras, in contrast to the usual configuration used in 3D TV, which are narrow baseline, parallel cameras. By using a backward mapping approach with a depth inpainting scheme based on median filters, we show that these techniques are adequate for free viewpoint video applications. In addition, we show that referring depth information to a global reference system is ill-advised and should be avoided. Then, we propose a background subtraction system based on kernel density estimation techniques. These techniques are very adequate for modelling complex scenes featuring multimodal backgrounds, but have not been so popular due to their huge computational and memory complexity. The proposed system, implemented in real time on a GPU, features novel proposals for dynamic kernel bandwidth estimation for the background model, selective update of the background model, update of the position of reference samples of the foreground model using a multi-region particle filter, and automatic selection of regions of interest to reduce computational cost. The results, evaluated on several databases and compared to other state-of-the-art algorithms, demonstrate the high quality and versatility of our proposal. Finally, we propose a general method for the approximation of arbitrarily complex functions using continuous piecewise linear functions, specially formulated for GPU implementation by leveraging their texture filtering units, normally unused for numerical computation. Our proposal features a rigorous mathematical analysis of the approximation error in function of the number of samples, as well as a method to obtain a suboptimal partition of the domain of the function to minimize approximation error.

Computer-aided drug design and ADMET predictions for identification and evaluation of novel potential farnesyltransferase inhibitors in cancer therapy

We have used various computational methodologies including molecular dynamics, density functional theory, virtual screening, ADMET predictions and molecular interaction field studies to design and analyze four novel potential inhibitors of farnesyltransferase (FTase). Evaluation of two proposals regarding their drug potential as well as lead compounds have indicated them as novel promising FTase inhibitors, with theoretically interesting pharmacotherapeutic profiles, when Compared to the very active and most cited FTase inhibitors that have activity data reported, which are launched drugs or compounds in clinical tests. One of our two proposals appears to be a more promising drug candidate and FTase inhibitor, but both derivative molecules indicate potentially very good pharmacotherapeutic profiles in comparison with Tipifarnib and Lonafarnib, two reference pharmaceuticals. Two other proposals have been selected with virtual screening approaches and investigated by LIS, which suggest novel and alternatives scaffolds to design future potential FTase inhibitors. Such compounds can be explored as promising molecules to initiate a research protocol in order to discover novel anticancer drug candidates targeting farnesyltransferase, in the fight against cancer. (C) 2009 Elsevier Inc. All rights reserved.

Video Object Tracking And Analysis For Computer Assisted Surgery

Pedicle screw insertion technique has made revolution in the surgical treatment of spinal fractures and spinal disorders. Although X- ray fluoroscopy based navigation is popular, there is risk of prolonged exposure to X- ray radiation. Systems that have lower radiation risk are generally quite expensive. The position and orientation of the drill is clinically very important in pedicle screw fixation. In this paper, the position and orientation of the marker on the drill is determined using pattern recognition based methods, using geometric features, obtained from the input video sequence taken from CCD camera. A search is then performed on the video frames after preprocessing, to obtain the exact position and orientation of the drill. An animated graphics, showing the instantaneous position and orientation of the drill is then overlaid on the processed video for real time drill control and navigation