399 Works

A Creative First Assignment in the Modern Graphics Pipeline

Elodie Fourquet & Lillian Pentecost
This paper describes a first assignment in an Introduction to Computer Graphics course taken by undergraduate students at a liberal arts college. The assignment marries the technical challenges found at the lowest level of the modern graphics pipeline with the artistic concerns of reproducing a piece of art. To do so, students extend provided code in WebGL, which includes GLSL shaders and no additional libraries, to reproduce a work of art of their own choosing....

RIFNOM: 3D Rotation-Invariant Features on Normal Maps

Akihiro Nakamura, Leo Miyashita, Yoshihiro Watanabe & Masatoshi Ishikawa
This paper presents 3D rotation-invariant features on normal maps: RIFNOM.We assign a local coordinate system (CS) to each pixel by using neighbor normals to extract the 3D rotation-invariant features. These features can be used to perform interest point matching between normal maps. We can estimate 3D rotations between corresponding interest points by comparing local CSs. Experiments with normal maps of a rigid object showed the performance of the proposed method in estimating 3D rotations. We...

Exemplar Based Filtering of 2.5D Meshes of Faces

Leandro Dihl, Leandro Cruz & Nuno Gonçalves
In this work, we present a content-aware filtering for 2.5D meshes of faces. We propose an exemplar-based filter that corrects each point of a given mesh through local model-exemplar neighborhood comparison. We take advantage of prior knowledge of the models (faces) to improve the comparison. We first detect facial feature points, and create the point correctors for regions of each feature, and only use the correspondent regions for correcting a point of the filtered mesh.

Time-Reversed Art Directable Smoke Simulation

Jeremy Oborn, Sean Flynn, Parris Egbert & Seth Holladay
Physics-based fluid simulation often produces unpredictable behavior that is difficult for artists to control. We present a new method for art directing smoke animation using time-reversed simulation. Given a final fluid configuration, our method steps backward in time generating a sequence that, when played forward, is visually similar to traditional forward simulations. This allows artists to create simulations with fast turnaround times that match an exact art-directed shape at any timestep of the simulation. We...

Optimized Sampling for View Interpolation in Light Fields with Overlapping Patches

David C. Schedl & Oliver Bimber
Optimized sampling masks that reduce the complexity of camera arrays while preserving the quality of light fields captured at high directional sampling resolution are presented. We propose a new quality metric that is based on sampling-theoretic considerations, a new mask estimation approach that reduces the search space by applying regularity and symmetry constraints, and an enhanced upsampling technique using compressed sensing that supports maximal patch overlap. Our approach out-beats state-of-the-art view-interpolation techniques for light fields...

Creating New Chinese Fonts based on Manifold Learning and Adversarial Networks

Yuan Guo, Zhouhui Lian, Yingmin Tang & Jianguo Xiao
The design of fonts, especially Chinese fonts, is known as a tough task that requires considerable time and professional skills. In this paper, we propose a method to easily generate Chinese font libraries in new styles based on manifold learning and adversarial networks. Starting from a number of existing fonts that cover various styles, we firstly use convolutional neural networks to obtain the representation features of these fonts, and then build a font manifold via...

Image-Based Information Visualization Tutorial

Christophe Hurter
While many data exploration techniques are based on automatic knowledge extraction, other tools exist where the user plays the central role. This tutorial will report actual use-cases where the user interactively explores datasets and extracts relevant information. These techniques must be interactive enough to insure flexibility data exploration, therefore image-based algorithms propose a suitable solution. These algorithms, processed in parallel by the graphic card, are fast and scalable enough to support interactive big data exploration...

Understanding Mystery Behind Example-Based Image Synthesis

J. Lu, M. Lukác & Daniel Sýkora
This tutorial presents a concise overview of development in the field of example-based image synthesis that over the last two decades rapidly evolved into a powerful tool enabling the production of synthetic imagery often indistinguishable from the source exemplar.We discuss not only the basic algorithmic concepts but also their further improvements which lead to significant reduction of computational overhead as well as better visual quality. We also demonstrate numerous applications including texture synthesis, hole-filling, video...

Comparison of Mixed Linear Complementarity Problem Solvers for Multibody Simulations with Contact

Andreas Enzenhöfer, Sheldon Andrews, Marek Teichmann & József Kövecses
The trade-off between accuracy and computational performance is one of the central conflicts in real-time multibody simulations, much of which can be attributed to the method used to solve the constrained multibody equations. This paper examines four mixed linear complementarity problem (MLCP) algorithms when they are applied to physical problems involving frictional contact. We consider several different, and challenging, test cases such as grasping, stability of static models, closed loops, and long chains of bodies....

The Impact of Passive Head-Mounted Virtual Reality Devices on the Quality of EEG Signals

Grégoire Cattan, Anton Andreev, Cesar Mendoza & Marco Congedo
Thanks to the low price, the use of a head-mounted device (HMD) equipped with a smartphone is currently a common set-up for virtual reality (VR). Brain-computer interface (BCI) based on electroencephalography (EEG) is a promising technology to enrich the VR experience. However, the effect of using HMDs on the acquisition of EEG signals remains still unknown. In fact, the smartphone is placed close to the head where EEG sensors are located, thus the smartphoneâ˘AZ´s electronics...

MLS Pressure Extrapolation for the Boundary Handling in Divergence-Free SPH

Stefan Band, Christoph Gissler, Andreas Peer & Matthias Teschner
We propose a novel method to predict pressure values at boundary particles in incompressible divergence-free SPH simulations (DFSPH). Our approach employs Moving Least Squares (MLS) to predict the pressure at boundary particles. Therefore, MLS computes hyperplanes that approximate the pressure field at the interface between fluid and boundary particles. We compare this approach with two previous techniques. One previous technique mirrors the pressure from fluid to boundary particles. The other one extrapolates the pressure from...

An Accelerated Online PCA with O(1) Complexity for Learning Molecular Dynamics Data

Salaheddin Alakkari & John Dingliana
In this paper, we discuss the problem of decomposing complex and large Molecular Dynamics trajectory data into simple low-resolution representation using Principal Component Analysis (PCA). Since applying standard PCA for such large data is expensive in terms of space and time complexity, we propose a novel online PCA algorithm with O(1) complexity per new timestep. Our approach is able to approximate the full dimensional eigenspace per new time-step of MD simulation. Experimental results indicate that...

Mol*: Towards a Common Library and Tools for Web Molecular Graphics

David Sehnal, Alexander Rose, Jaroslav Koca, Stephen Burley & Sameer Velankar
Advances in experimental techniques are providing access to structures of ever more complex and larger macromolecular systems. Web-browser based visualization and analysis of macromolecular structures and associated data represents a crucial step in gaining knowledge from these data. A common library and a set of tools for working with such macromolecular data sets would streamline this step. We present a project called Mol* (/'mol-star/) whose goal is to provide a common library and a set...

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...

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...

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....

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...

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...

Scalable Real-Time Shadows using Clustering and Metric Trees

François Deves, Frédéric Mora, Lilian Aveneau & Djamchid Ghazanfarpour
Real-time shadow algorithms based on geometry generally produce high quality shadows. Recent works have considerably improved their efficiency. However, scalability remains an issue because these methods strongly depend on the geometric complexity. This paper focuses on this problem. We present a new real-time shadow algorithm for non-deformable models that scales the geometric complexity. Our method groups triangles into clusters by precomputing bounding spheres or bounding capsules (line-swept spheres). At each frame, we build a ternary...

Screen Space Approximate Gaussian Hulls

Julian Meder & Beat Brüderlin
The Screen Space Approximate Gaussian Hull method presented in this paper is based on an output sensitive, adaptive approach, which addresses the challenge of high quality rendering even for high resolution displays and large numbers of light sources or indirect lighting. Our approach uses dynamically sparse sampling of the light information on a low-resolution mesh approximated from screen space and applying these samples in a deferred shading stage to the full resolution image. This preserves...

Registration Year

  • 2018

Resource Types

  • Text