Fitting 3D morphable models using implicit representations

We consider the problem of approximating the 3D scan of a real object through an affine combination of examples. Common approaches depend either on the explicit estimation of point-to-point correspondences or on 2-dimensional projections of the target mesh; both present drawbacks. We follow an approach similar to [IF03] by representing the target via an implicit function, whose values at the vertices of the approximation are used to define a robust cost function. The problem is approached in two steps, by approximating first a coarse implicit representation of the whole target, and then finer, local ones; the local approximations are then merged together with a Poisson-based method. We report the results of applying our method on a subset of 3D scans from the Face Recognition Grand Challenge v.1.0.

3D Face Reconstruction from 2D Pictures: First Results of a Web-Based Computer Aided System for Aesthetic Procedures

The human face is a vital component of our identity and many people undergo medical aesthetics procedures in order to achieve an ideal or desired look. However, communication between physician and patient is fundamental to understand the patient’s wishes and to achieve the desired results. To date, most plastic surgeons rely on either “free hand” 2D drawings on picture printouts or computerized picture morphing. Alternatively, hardware dependent solutions allow facial shapes to be created and planned in 3D, but they are usually expensive or complex to handle. To offer a simple and hardware independent solution, we propose a web-based application that uses 3 standard 2D pictures to create a 3D representation of the patient’s face on which facial aesthetic procedures such as filling, skin clearing or rejuvenation, and rhinoplasty are planned in 3D. The proposed application couples a set of well-established methods together in a novel manner to optimize 3D reconstructions for clinical use. Face reconstructions performed with the application were evaluated by two plastic surgeons and also compared to ground truth data. Results showed the application can provide accurate 3D face representations to be used in clinics (within an average of 2 mm error) in less than 5 min.

Development of a 3D Game Engine

This paper presents the development history and specification of a 3D game engine titled "Spark Engine". The term "engine" is used to describe a complex graphics software suite that streamlines application development and provides efficient rendering functionality. A game engine specifically provides tools to simplify game development. Spark Engine is fully shader driven and is built on top of Microsoft's XNA Framework. It is a reusable and flexible platform that can be used to build any type of graphics application ranging from gaming to simulation. The engine was released as open source software under the New BSD License with an interest in furthering its development.

Seamless, Static Multi-Texturing of 3D Meshes

In the context of 3D reconstruction, we present a static multi-texturing system yielding a seamless texture atlas calculated by combining the colour information from several photos from the same subject covering most of its surface. These pictures can be provided by shooting just one camera several times when reconstructing a static object, or a set of synchronized cameras, when dealing with a human or any other moving object. We suppress the colour seams due to image misalignments and irregular lighting conditions that multi-texturing approaches typically suffer from, while minimizing the blurring effect introduced by colour blending techniques. Our system is robust enough to compensate for the almost inevitable inaccuracies of 3D meshes obtained with visual hull–based techniques: errors in silhouette segmentation, inherently bad handling of concavities, etc.

Multi-textured 3D humanoid reconstruction through passive and active automatic techniques = Reconstrucción de humanoides 3D multi-texturados mediante técnicas pasivas y activas automáticas

The proliferation of video games and other applications of computer graphics in everyday life demands a much easier way to create animatable virtual human characters. Traditionally, this has been the job of highly skilled artists and animators that painstakingly model, rig and animate their avatars, and usually have to tune them for each application and transmission/rendering platform. The emergence of virtual/mixed reality environments also calls for practical and costeffective ways to produce custom models of actual people. The purpose of the present dissertation is bringing 3D human scanning closer to the average user. For this, two different techniques are presented, one passive and one active. The first one is a fully automatic system for generating statically multi-textured avatars of real people captured with several standard cameras. Our system uses a state-of-the-art shape from silhouette technique to retrieve the shape of subject. However, to deal with the lack of detail that is common in the facial region for these kind of techniques, which do not handle concavities correctly, our system proposes an approach to improve the quality of this region. This face enhancement technique uses a generic facial model which is transformed according to the specific facial features of the subject. Moreover, this system features a novel technique for generating view-independent texture atlases computed from the original images. This static multi-texturing system yields a seamless texture atlas calculated by combining the color information from several photos. We suppress the color seams due to image misalignments and irregular lighting conditions that multi-texturing approaches typically suffer from, while minimizing the blurring effect introduced by color blending techniques. The second technique features a system to retrieve a fully animatable 3D model of a human using a commercial depth sensor. Differently to other approaches in the current state of the art, our system does not require the user to be completely still through the scanning process, and neither the depth sensor is moved around the subject to cover all its surface. Instead, the depth sensor remains static and the skeleton tracking information is used to compensate the user’s movements during the scanning stage. RESUMEN La popularización de videojuegos y otras aplicaciones de los gráficos por ordenador en el día a día requiere una manera más sencilla de crear modelos virtuales humanos animables. Tradicionalmente, estos modelos han sido creados por artistas profesionales que cuidadosamente los modelan y animan, y que tienen que adaptar específicamente para cada aplicación y plataforma de transmisión o visualización. La aparición de los entornos de realidad virtual/mixta aumenta incluso más la demanda de técnicas prácticas y baratas para producir modelos 3D representando personas reales. El objetivo de esta tesis es acercar el escaneo de humanos en 3D al usuario medio. Para ello, se presentan dos técnicas diferentes, una pasiva y una activa. La primera es un sistema automático para generar avatares multi-texturizados de personas reales mediante una serie de cámaras comunes. Nuestro sistema usa técnicas del estado del arte basadas en shape from silhouette para extraer la forma del sujeto a escanear. Sin embargo, este tipo de técnicas no gestiona las concavidades correctamente, por lo que nuestro sistema propone una manera de incrementar la calidad en una región del modelo que se ve especialmente afectada: la cara. Esta técnica de mejora facial usa un modelo 3D genérico de una cara y lo modifica según los rasgos faciales específicos del sujeto. Además, el sistema incluye una novedosa técnica para generar un atlas de textura a partir de las imágenes capturadas. Este sistema de multi-texturización consigue un atlas de textura sin transiciones abruptas de color gracias a su manera de mezclar la información de color de varias imágenes sobre cada triángulo. Todas las costuras y discontinuidades de color debidas a las condiciones de iluminación irregulares son eliminadas, minimizando el efecto de desenfoque de la interpolación que normalmente introducen este tipo de métodos. La segunda técnica presenta un sistema para conseguir un modelo humano 3D completamente animable utilizando un sensor de profundidad. A diferencia de otros métodos del estado de arte, nuestro sistema no requiere que el usuario esté completamente quieto durante el proceso de escaneado, ni mover el sensor alrededor del sujeto para cubrir toda su superficie. Por el contrario, el sensor se mantiene estático y el esqueleto virtual de la persona, que se va siguiendo durante el proceso, se utiliza para compensar sus movimientos durante el escaneado.

Anatomofisiologia da sucção e deglutição do bebê em computação gráfica 3D como instrumento educacional

A eficiência da amamentação exige uma complexa coordenação entre sucção, deglutição e respiração, sendo que a tecnologia tem possibilitado importantes avanços na compreensão desse processo. Porém, não foram encontrados vídeos disponíveis na internet que demonstrassem a anatomia e fisiologia da amamentação, de modo didático e fidedigno à ciência atual. Este trabalho teve por objetivo descrever o desenvolvimento de uma sequência em computação gráfica sobre a sucção e a deglutição, resultante da produção digital do Bebê Virtual, bem como validar tal produção quanto ao conteúdo e prover adequações necessárias ao material educacional. Para a produção das iconografias em 3D da sucção e deglutição no Bebê Virtual, inicialmente foi elaborado um mapa conceitual e uma matriz de conteúdos, objetivos e competências voltadas ao material educacional. Posteriormente foi elaborado um roteiro científico que abordou a anatomia do crânio, face, cavidade oral, faringe, laringe e esôfago do recém-nascido, bem como, a descrição dos mecanismos fisiológicos relacionados à sucção e às fases oral e faríngea da deglutição no bebê. Para isso foram utilizadas 14 publicações do período de 1998 a 2008, que continham informações relevantes para demonstrar a amamentação. Os conteúdos teóricos foram organizados em cenas principais, possibilitando a criação de previews das sequências dinâmicas, as quais foram avaliadas por profissionais de anatomia, fonoaudiologia e medicina, possibilitando os ajustes necessários e a construção das imagens em computação gráfica 3D. Para análise da validade de conteúdo dessas imagens foi verificada a representatividade dos itens que o compõe, por meio de consulta à literatura. Foram incluídos estudos que utilizaram auxílio tecnológico e abordaram o tema proposto em bebês a termo e saudáveis, sem alterações neurológicas ou anomalias craniofaciais. Foram excluídas as publicações realizadas com bebês pré-termo, sindrômicos, com anomalias, doenças neurológicas ou qualquer alteração que pudesse interferir na amamentação, revisões de literatura e relatos de caso. Os artigos selecionados foram analisados e classificados quanto ao nível de evidência científica, predominando o nível três de evidência. A análise de conteúdo demonstrou a necessidade de adequações nas iconografias 3D, para que o processo de sucção e deglutição demonstrado no bebê virtual pudesse corresponder ao conhecimento científico atual. Tais adequações foram propostas a partir dos achados de 9 estudos, publicados entre 2008 e 2014, que utilizaram ultrassonografia para demonstrar como ocorre o processo de amamentação. Desta forma, foram modificados os aspectos da pega, da movimentação de língua, mandíbula, palato mole e laringe, além da sincronização da sucção/deglutição/respiração e deslocamento do mamilo, num processo desenvolvido em cinco etapas. Assim, o presente estudo descreveu o processo de desenvolvimento das iconografias em 3D sobre a anatomia e fisiologia da sucção e deglutição no recém-nascido a termo, sendo que a validade de conteúdo permitiu atualizar vários aspectos da amamentação do Bebê Virtual, quebrando velhos paradigmas e possibilitando ilustrar didaticamente as evidências científicas relacionadas.

Interactive Visualization of the Building of University of Economics – Varna via 3D Modeling

The object of this paper is presenting the University of Economics – Varna, using a 3D model with 3Ds MAX. Created in 1920, May 14, University of Economics - Varna is a cultural institution with a place and style of its own. With the emergence of the three-dimensional modeling we entered a new stage of the evolution of computer graphics. The main target is to preserve the historical vision, to demonstrate forward-thinking and using of future-oriented approaches.

A Framework for Realistic 3D Tele-Immersion

Meeting, socializing and conversing online with a group of people using teleconferencing systems is still quite different from the experience of meeting face to face. We are abruptly aware that we are online and that the people we are engaging with are not in close proximity. Analogous to how talking on the telephone does not replicate the experience of talking in person. Several causes for these differences have been identified and we propose inspiring and innovative solutions to these hurdles in attempt to provide a more realistic, believable and engaging online conversational experience. We present the distributed and scalable framework REVERIE that provides a balanced mix of these solutions. Applications build on top of the REVERIE framework will be able to provide interactive, immersive, photo-realistic experiences to a multitude of users that for them will feel much more similar to having face to face meetings than the experience offered by conventional teleconferencing systems.

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

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.

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.

3D-Pharmacophore mapping of thymidine-based inhibitors of TMPK as potential antituberculosis agents

Tuberculosis (TB) is the primary cause of mortality among infectious diseases. Mycobacterium tuberculosis monophosphate kinase (TMPKmt) is essential to DNA replication. Thus, this enzyme represents a promising target for developing new drugs against TB. In the present study, the receptor-independent, RI, 4D-QSAR method has been used to develop QSAR models and corresponding 3D-pharmacophores for a set of 81 thymidine analogues, and two corresponding subsets, reported as inhibitors of TMPKmt. The resulting optimized models are not only statistically significant with r (2) ranging from 0.83 to 0.92 and q (2) from 0.78 to 0.88, but also are robustly predictive based on test set predictions. The most and the least potent inhibitors in their respective postulated active conformations, derived from each of the models, were docked in the active site of the TMPKmt crystal structure. There is a solid consistency between the 3D-pharmacophore sites defined by the QSAR models and interactions with binding site residues. Moreover, the QSAR models provide insights regarding a probable mechanism of action of the analogues.

Algorismes de shading moderns|h[Recurs electrònic] :|b implementació i comparativa

Elmercat de jocs i de pel•lícules d'entreteniment demana constantment entornsmés realistes i efectes que sorprenguin a l'espectador.Els gràfics 3D interactius (per exemple, dels jocs) han vist una evoluciósorprenent en les dues últimes dècades. Hem passat de representacions moltesquemàtiques i simplificades dels entorns, a una qualitat visual que aviatserà indistingible de la realitat. El projecte tracta de desenvolupar un motor 3D des de zero. Es podria haver utilitzatun motor 3D ja disponible com a base, com per exemple el popular Unity,però s’ha decidit crear-lo ja que això dóna l’ oportunitat de conèixer com funcionen els motoscomercials i provar noves idees. En resum, és un treball difícil, però moltenriquidor, la qual cosa comporta una gran motivacio.S’han utilitzat noves tecnologies. No només s’ha volgut desenvoluparun motor 3D des de zero, si no que s’han volgut provar noves llibreries gràfiques i nous formats de dades 3d. El mercat té força oferta de les duess, per la qualcosa s’ha aprofitat l’ oportunitat per aprendre duess tecnologies noves.El procés de desenvolupar un projecte utilitzant tecnologies desconegudes permetrà aprendre els seus punts forts i febles, podent fer-neuna anàlisi crítica, que d'altra manera no es tindria.Finalment, s’ha implementat i comparat quatre algorismes de shading.La selecció dels quatre algorismes ha estat en base a les diferentsnecessitats que intenten cobrir. El primer, el Forward Shading, és l'algorismeclàssic, utilitzat des de fa dècades, però que teòricament escala malament respecte a la quantitat de llums. El segon, el Deferred Shading, teòricament,escala molt bé amb moltes llums, però té un cost base elevat, i un consum altde memòria. El tercer, el Deferred Lighting, és una variació de l'anterior queintenta reduir el cost base i l'úss de memòria. L'últim, el Inferred Lighting,intenta explotar la baixa freqüència de la il•luminació dels entorns 3D, persuportar una gran quantitat de llums amb un molt bon rendiment.Un cop implementats aquests quatre algorismes, s’han pogut compararrespecte el seu ús de la GPU, i el seu comportament en diferents tipusd'escenes, per tal de tenir una visió global de quin algorisme és adequat encada situació

Open source solutions for multiplatform graphics programming

New emerging technologies in the recent decade have brought new options to cross platform computer graphics development. This master thesis took a look for cross platform 3D graphics development possibilities. All platform dependent and non real time solutions were excluded. WebGL and two different OpenGL based solutions were assessed via demo application by using most recent development tools. In the results pros and cons of the each solutions were noted.

3D scanning by multiple fan beam X-ray sources and sensors

*** Purpose – Computer tomography (CT) for 3D reconstruction entails a huge number of coplanar fan-beam projections for each of a large number of 2D slice images, and excessive radiation intensities and dosages. For some applications its rate of throughput is also inadequate. A technique for overcoming these limitations is outlined. *** Design methodology/approach – A novel method to reconstruct 3D surface models of objects is presented, using, typically, ten, 2D projective images. These images are generated by relative motion between this set of objects and a set of ten fanbeam X-ray sources and sensors, with their viewing axes suitably distributed in 2D angular space. *** Findings – The method entails a radiation dosage several orders of magnitude lower than CT, and requires far less computational power. Experimental results are given to illustrate the capability of the technique *** Practical implications – The substantially lower cost of the method and, more particularly, its dramatically lower irradiation make it relevant to many applications precluded by current techniques *** Originality/value – The method can be used in many applications such as aircraft hold-luggage screening, 3D industrial modelling and measurement, and it should also have important applications to medical diagnosis and surgery.