399 Works

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...

Frontmatter: ACM SIGGRAPH / Eurographics Symposium of Computer Animation 2018 - Posters

Melina Skouras

Latent Motion Manifold with Sequential Auto-Encoders

Deok-Kyeong Jang & Sung-Hee Lee
We propose the sequential autoencoders for constructing latent motion manifold. Sequential autoencoders minimize the difference between the ground truth motion space distribution and reconstructed motion space distribution sampled from the latent motion manifold. Our method is based on sequence-to-sequence model for encoding the temporal information of human motion. We also adopt Wasserstein regularizer for matching encoded training distribution to the prior distribution of motion manifold. Our experiments show that randomly sampled points from trained motion...

VR Kino+Theatre: From the Ancient Greeks Into the Future of Media

Luiz Velho, Leonardo Carvalho & Djalma Lucio
VR Kino+Theatre is a media platform that combines theatrical performance with live cinema using virtual reality technology.

A Study on Natural 3D Shape Manipulation in VR

E. Cordeiro, F. Giannini, M. Monti, D. Mendes & A. Ferreira
Current immersive modeling environments use non-natural tools and interfaces to support traditional shape manipulation operations. In the future, we expect the availability of natural methods of interaction with 3D models in immersive environments to become increasingly important in several industrial applications. In this paper, we present a study conducted on a group of potential users with the aim of verifying if there is a common strategy in gestural and vocal interaction in immersive environments when...

An Optimized Marker Layout for 3D Facial Motion Capture

A. D. Will, J. M. De Martino & J. Bezerra
Facial motion capture (Facial Mocap) has gained increasing attention from researchers and professionals from different areas of interest, including entertainment, face-to-face communication, and training. Facial Mocap allows straightforward capture of dynamic behavior of the face from live action, providing data that can be used to drive realistic animation of a 3D virtual face. Facial Mocap is an advantageous alternative to the direct and laborious manipulation of the face model. In particular, marker-based mocap technique acquires...

Towards the Reconstruction of Wide Historical Sites: A Local Graph-based Representation to Resample Gigantic Acquisitions

Arnaud Bletterer, Frédéric Payan, Marc Antonini & Anis Meftah
Nowadays, LiDAR scanners are able to digitize very wide historical sites, leading to point clouds composed of billions of points. These point clouds are able to describe very small objects or elements disseminated in these sites, but also exhibit numerous defects in terms of sampling quality. Moreover, they sometimes contain too many samples to be processed as they are. In this paper, we propose a local graph-based structure to deal with the set of LiDAR...

Frontmatter: Eurographics Workshop on Graphics and Cultural Heritage

Robert Sablatnig & Michael Wimmer

Improving Marker-Based Tracking for Augmented Reality in Underwater Environments

Jan Cejka, Marek Zuzi, Panagiotis Agrafiotis, Dimitrios Skarlatos, Fabio Bruno & Fotis Liarokapis
Underwater sites are a challenging environment for augmented reality. Images taken under water are degraded in several ways, most importantly they are affected by unbalanced colors due to uneven absorption of light in each color channel, blurring and desaturation caused by turbidity, or noise due to the presence of larger organisms, plants, or bubbles. In this paper, we introduce a new method based on white balancing that enhances underwater images to improve the results of...

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.

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....

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...

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...

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....

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...

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...

Protein Shape Retrieval

Florent Langenfeld, Apostolos Axenopoulos, Anargyros Chatzitofis, Daniela Craciun, Petros Daras, Bowen Du, Andrea Giachetti, Yu-Kun Lai, Haisheng Li, Yingbin Li, Majid Masoumi, Yuxu Peng, Paul L. Rosin, Jeremy Sirugue, Li Sun, Spyridon Thermos, Matthew Toews, Yang Wei, Yujuan Wu, Yujia Zhai, Tianyu Zhao, Yanping Zheng & Matthieu Montes
Proteins are macromolecules central to biological processes that display a dynamic and complex surface. They display multiple conformations differing by local (residue side-chain) or global (loop or domain) structural changes which can impact drastically their global and local shape. Since the structure of proteins is linked to their function and the disruption of their interactions can lead to a disease state, it is of major importance to characterize their shape. In the present work, we...

Completion of Cultural Heritage Objects with Rotational Symmetry

Ivan Sipiran
Archaeological artifacts are an important part of our cultural heritage. They help us understand how our ancestors used to live. Unfortunately, many of these objects are badly damaged by the passage of time and need repair. If the object exhibits some form of symmetry, it is possible to complete the missing regions by replicating existing parts of the object. In this paper, we present a framework to complete 3D objects that exhibit rotational symmetry. Our...

Frontmatter: ICAT-EGVE 2018 - International Conference on Artificial Reality and Telexistence and Eurographics Symposium on Virtual Environments

Gerd Bruder, Shunsuke Yoshimoto & Sue Cobb

Analysis of Spatio-temporal Data in Virtual Historic Spaces

Georgios Artopoulos & Panayiotis Charalambous
This paper presents a virtual reality workflow for citizen engagement in the management of neglected historic sites in contested cities, such as Nicosia, Cyprus, the last divided capital of Europe. It is contextualized in an ongoing research for the use of interactive visualization technologies for co-creation and co-management design practices in public space management. We demonstrate initial results from tracking the movement and gaze of users in VR walkthroughs of a historic site with and...

Registration Year

  • 2018
    399

Resource Types

  • Text
    239