399 Works

Automatic Infant Face Verification via Convolutional Neural Networks

Leslie Wöhler, Hangjian Zhang, Georgia Albuquerque & Marcus Magnor
In this paper, we investigate how convolutional neural networks (CNN) can learn to solve the verification task for faces of young children. One of the main issues of automatic face verification approaches is how to deal with facial changes resulting from aging. Since the facial shape and features change drastically during early childhood, the recognition of children can be challenging even for human observers. Therefore, we design CNNs that take two infant photographs as input...

Hierarchical Additive Poisson Disk Sampling

Alexander Dieckmann & Reinhard Klein
Generating samples of point clouds and meshes with blue noise characteristics is desirable for many applications in rendering and geometry processing. Working with laser-scanned or lidar point clouds, we usually find region with artifacts called scanlines and scan-edges. These regions are problematic for geometry processing applications, since it is not clear how many points should be selected to define a proper neighborhood. We present a method to construct a hierarchical additive poisson disk sampling from...

Gauss-Seidel Progressive Iterative Approximation (GS-PIA) for Loop Surface Interpolation

Zhihao Wang, Yajuan Li, Weiyin Ma & Chongyang Deng
We propose a Gauss-Seidel progressive iterative approximation (GS-PIA) method for Loop subdivision surface interpolation by combining classical Gauss-Seidel iterative method for linear system and progressive iterative approximation (PIA) for data interpolation. We prove that GS-PIA is convergent by applying matrix theory. GS-PIA algorithm retains the good features of the classical PIA method, such as the resemblance with the given mesh and the advantages of both a local method and a global method. Compared with some...

Topological Connected Chain Modelling for Classification of Mammographic Microcalcification

Minu George, Erika R. E. Denton & Reyer Zwiggelaar
Breast cancer continues to be the most common type of cancer among women. Early detection of breast cancer is key to effective treatment. The presence of clusters of fine, granular microcalcifications in mammographic images can be a primary sign of breast cancer. The malignancy of any cluster of microcalcification cannot be reliably determined by radiologists from mammographic images and need to be assessed through histology images. In this paper, a novel method of mammographic microcalcification...

Groupwise Non-rigid Image Alignment With Graph-based Initialisation

Ahmad Aal-Yhia, Paul Malcolm, Otar Akanyeti, Reyer Zwiggelaar & Bernard Tiddeman
Groupwise image alignment automatically provides non-rigid registration across a set of images. It has found applications in facial image analysis and medical image analysis by automatically generating statistical models of shape and appearance. The main approaches used previously include iterative and graph-based approaches. In iterative approaches, the registration of each image is iteratively updated to minimise an error measure across the set. Various metrics and optimisation strategies have been proposed to achieve this. Graph-based methods...

Visual Analysis of Regional Anomalies in Myocardial Motion

Ali Sheharyar, Alexander Ruh, Maria Aristova, Michael Scott, Kelly Jarvis, Mohammed Elbaz, Ryan Dolan, Susanne Schnell, Kal Lin, James Carr, Michael Markl, Othmane Bouhali & Lars Linsen
Regional anomalies in the myocardial motion of the left ventricle (LV) are important biomarkers for several cardiac diseases. Myocardial motion can be captured using a velocity-encoded magnetic resonance imaging method called tissue phase mapping (TPM). The acquired data are pre-processed and represented as regional velocities in cylindrical coordinates at three short-axis slices of the left ventricle over one cardiac cycle. We use a spatio-temporal visualization based on a radial layout where the myocardial regions are...

VisualFlatter - Visual Analysis of Distortions in the Projection of Biomedical Structures

Nicolas Grossmann, Thomas Köppel, Eduard Gröller & Renata Georgia Raidou
Projections of complex anatomical or biological structures from 3D to 2D are often used by visualization and domain experts to facilitate inspection and understanding. Representing complex structures, such as organs or molecules, in a simpler 2D way often requires less interaction, while enabling comparability. However, the most commonly employed projection methods introduce size or shape distortions, in the resulting 2D representations. While simple projections display known distortion patterns, more complex projection algorithms are not easily...

Introducing CNN-Based Mouse Grim Scale Analysis for Fully Automated Image-Based Assessment of Distress in Laboratory Mice

Marcin Kopaczka, Lisa Ernst, Justus Schock, Arne Schneuing, Alexander Guth, Rene Tolba & Dorit Merhof
International standards require close monitoring of distress of animals undergoing laboratory experiments in order to minimize the stress level and allow choosing minimally stressful procedures for the experiments. Currently, one of the the best established severity assessment procedures is the mouse grimace scale (MGS), a protocol in which images of the animals are taken and scored by assessing five key visual features that have been shown to be highly correlated with distress and pain. While...

Uncertainty-Guided Semi-Automated Editing of CNN-based Retinal Layer Segmentations in Optical Coherence Tomography

Shekoufeh Gorgi Zadeh, Maximilian W. M. Wintergerst & Thomas Schultz
Convolutional neural networks (CNNs) have enabled dramatic improvements in the accuracy of automated medical image segmentation. Despite this, in many cases, results are still not reliable enough to be trusted ''blindly''. Consequently, a human rater is responsible to check correctness of the final result and needs to be able to correct any segmentation errors that he or she might notice. For a particular use case, segmentation of the retinal pigment epithelium and Bruch's membrane from...

Frontmatter: Eurographics Workshop on Visual Computing for Biology and Medicine 2018

Anna Puig Puig, Thomas Schultz, Anna Vilanova, Ingrid Hotz, Barbora Kozlikova & Pere-Pau Vázquez

A Prototype Holographic Augmented Reality Interface for Image-Guided Prostate Cancer Interventions

Cristina M. Morales Mojica, Jose D. Velazco Garcia, Nikhil V. Navkar, Shidin Balakrishnan, Julien Abinahed, Walid El Ansari, Khalid Al-Rumaihi, Adham Darweesh, Abdulla Al-Ansari, Mohamed Gharib, Mansour Karkoub, Ernst L. Leiss, Ioannis Seimenis & Nikolaos V. Tsekos
Motivated by the potential of holographic augmented reality (AR) to offer an immersive 3D appreciation of morphology and anatomy, the purpose of this work is to develop and assess an interface for image-based planning of prostate interventions with a head-mounted display (HMD). The computational system is a data and command pipeline that links a magnetic resonance imaging (MRI) scanner/data and the operator, that includes modules dedicated to image processing and segmentation, structure rendering, trajectory planning...

Image-based Fitting of Procedural Yarn Models

Alina Saalfeld, Florian Reibold & Carsten Dachsbacher
While common in real life, rendering fiber and cloth accurately is challenging. Recent fiber-based, procedural rendering approaches proved to be able to capture a great amount of details of real yarn. However, the current automatic method of fitting the model parameters is expensive and inaccessible as it relies on micro CT scans of the reference yarn. The alternative is to have an artist fit the parameters by hand, which is impractical because of the large...

A Simple Diffuse Fluorescent BBRRDF Model

Alisa Jung, Johannes Hanika, Steve Marschner & Carsten Dachsbacher
Fluorescence - the effect of a photon being absorbed at one wavelength and re-emitted at another - is present in many common materials such as clothes and paper. Yet there has been little research in rendering or modeling fluorescent surfaces. We discuss the design decisions leading to a simple model for a diffuse fluorescent BBRRDF (bispectral bidirectional reflection and reradiation distribution function). In contrast to reradiation matrix based models our model is continuous in wavelength...

Muscle Simulation with Extended Position Based Dynamics

Marco Romeo, Carlos Monteagudo & Daniel Sánchez-Quirós
Recent research on muscle simulation for Visual Effects relies on numerical methods such as the Finite Element Method or Finite Volume Method. These approaches produce realistic results, but require high computational time and are complex to set up. On the other hand Position Based Dynamics offers a fast and controllable solution to simulate surfaces and volumes, but there is no literature on how to implement constraints that could be used to realistically simulate muscles for...

FORHHSS-TEA, Support to the Individual Work System for People With Autism Spectrum Disorder Using Virtual and Augmented Reality

Javier Sevilla, Lucia Vera, Gerardo Herrera & Marcos Fernández
The Individual Work System (IWS) is an essential element from the TEACCH program, designed by The University of North Carolina (USA), one of the most used all over the world for work with persons with Autism Spectrum Disorder (ASD). The FORHHSS-TEA project uses spatial augmented reality and virtual reality technologies, following the IWS, to help persons with ASD to develop areas where they usually have problems. In the VR version, the end-users wear virtual reality...

On the Design of a Mixed-Reality Annotations Tool for the Inspection of Pre-fab Buildings

Inma García-Pereira, Jesús Gimeno, Cristina Portalés, María Vidal-González & Pedro Morillo
The introduction of Augmented Reality (AR) and Virtual Reality (VR) in the inspection works carried out during the construction of prefabricated buildings can allow the early detection and elimination of deviations in their quality and energy efficiency. These new tools let us change from the traditional note taking on paper to the use of an AR application that allows to make rich annotations. The later on-site or in-office revision of the information taken as well...

Experiences From the Development of a Prototype of an Spatial Augmented Reality System

José Luis Cárdenas-Donoso, Ángel-Luis García-Fernández, Francisco-De-Asís Conde-Rodríguez & Carlos-Javier Ogáyar-Anguita
This paper describes the hardware and software of a prototype of a portable Spatial Augmented Reality system. This prototype is completely autonomous and projects the information on the real world, so that it is visible for a group of users. The system was built using mostly low-cost hardware (Raspberry Pi, plus a camera module and an inertial measurement unit), and the software was developed using C++ and OpenGL ES 2.0.

Blast Features and Requirements for Fracturing Osseous Models

Francisco Daniel Pérez, Juan José Jiménez & Juan Roberto Jiménez
Fracturing osseous models is a challenge in computer graphics. The generation of bone fractures is important in the field of traumatology mainly for training. This field of research can provide specialists with a rich and varied amount of fracture cases. Traditionally, the generation of bone fractures has been carried out by using a finite element method (FEM) approach. Nevertheless, this approach requires a precise physical information of the model and the incoming forces that are...

Frontmatter: Symposium on Geometry Processing 2018 - Posters

Tao Ju & Amir Vaxman

Solving PDEs on Deconstructed Domains

Silvia Sellán, Herng Yi Cheng, Yuming Ma, Mitchell Dembowski & Alec Jacobson
When finding analytical solutions to Partial Differential Equations (PDEs) becomes impossible, it is useful to approximate them via a discrete mesh of the domain. Sometimes a robust triangular (2D) or tetrahedral (3D) mesh of the whole domain is a hard thing to accomplish, and in those cases we advocate for breaking up the domain in various different subdomains with nontrivial intersection and to find solutions for the equation in each of them individually. Although this...

Approximate svBRDF Estimation From Mobile Phone Video

Rachel A. Albert, Dorian Yao Chan, Dan B. Goldman & James F. O'Brien
We describe a new technique for obtaining a spatially varying BRDF (svBRDF) of a flat object using printed fiducial markers and a cell phone capable of continuous flash video. Our homography-based video frame alignment method does not require the fiducial markers to be visible in every frame, thereby enabling us to capture larger areas at a closer distance and higher resolution than in previous work. Pixels in the resulting panorama are fit with a BRDF...

A Unified Manifold Framework for Efficient BRDF Sampling based on Parametric Mixture Models

Sebastian Herholz, Oskar Elek, Jens Schindel, Jaroslav Křivánek & Hendrik P. A. Lensch
Virtually all existing analytic BRDF models are built from multiple functional components (e.g., Fresnel term, normal distribution function, etc.). This makes accurate importance sampling of the full model challenging, and so current solutions only cover a subset of the model's components. This leads to sub-optimal or even invalid proposed directional samples, which can negatively impact the efficiency of light transport solvers based on Monte Carlo integration. To overcome this problem, we propose a unified BRDF...

An Improved Multiple Importance Sampling Heuristic for Density Estimates in Light Transport Simulations

Johannes Jendersie & Thorsten Grosch
Vertex connection and merging (VCM) is one of the most robust light transport simulation algorithms developed so far. It combines bidirectional path tracing with photon mapping using multiple importance sampling (MIS). However, there are scene setups where the current weight computation is not optimal. If different merge events on a single path have roughly the same likelihood to be found, but different photon densities, this leads to high variance samples. We show how to improve...

Deep Hybrid Real and Synthetic Training for Intrinsic Decomposition

Sai Bi, Nima Khademi Kalantari & Ravi Ramamoorthi
Intrinsic image decomposition is the process of separating the reflectance and shading layers of an image, which is a challenging and underdetermined problem. In this paper, we propose to systematically address this problem using a deep convolutional neural network (CNN). Although deep learning (DL) has been recently used to handle this application, the current DL methods train the network only on synthetic images as obtaining ground truth reflectance and shading for real images is difficult....

Primary Sample Space Path Guiding

Jerry Jinfeng Guo, Pablo Bauszat, Jacco Bikker & Elmar Eisemann
Guiding path tracing in light transport simulation has been one of the practical choices for variance reduction in production rendering. For this purpose, typically structures in the spatial-directional domain are built. We present a novel scheme for unbiased path guiding. Different from existing methods, we work in primary sample space. We collect records of primary samples as well as the luminance that the resulting path contributes and build a multiple dimensional structure, from which we...

Registration Year

  • 2018
    399

Resource Types

  • Text
    239