EG2019

Permanent URI for this community

https://diglib.eg.org/handle/10.2312/2632746

Browse

Now showing 1 - 20 of 67

Optimal Deterministic Mixture Sampling
(The Eurographics Association, 2019) Sbert, Mateu; Havran, Vlastimil; Szirmay-Kalos, László; Cignoni, Paolo and Miguel, Eder
Multiple Importance Sampling (MIS) can combine several sampling techniques preserving their advantages. For example, we can consider different Monte Carlo rendering methods generating light path samples proportionally only to certain factors of the integrand. MIS then becomes equivalent to the application of the mixture of individual sampling densities, thus can simultaneously mimic the densities of all considered techniques. The weights of the mixture sampling depends on how many samples are generated with each particular method. This paper examines the optimal determination of this parameter. The proposed method is demonstrated with the combination of BRDF sampling and Light source sampling, and we show that it not only outperforms the application of the two individual methods, but is superior to other recent combination strategies and is close to the theoretical optimum.
VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss
(The Eurographics Association, 2019) Honda, Shion; Fusiello, Andrea and Bimber, Oliver
Generating a virtual try-on image from in-shop clothing images and a model person's snapshot is a challenging task because the human body and clothes have high flexibility in their shapes. In this paper, we develop a Virtual Try-on Generative Adversarial Network (VITON-GAN), that generates virtual try-on images using images of in-shop clothing and a model person. This method enhances the quality of the generated image when occlusion is present in a model person's image (e.g., arms crossed in front of the clothes) by adding an adversarial mechanism in the training pipeline.
EUROGRAPHICS 2019: Short Papers Frontmatter
(Eurographics Association, 2019) Cignoni, Paolo; Miguel, Eder; Cignoni, Paolo and Miguel, Eder
How to Write a Visualization Survey Paper: A Starting Point
(The Eurographics Association, 2019) McNabb, Liam; Laramee, Robert S.; Tarini, Marco and Galin, Eric
This paper attempts to explain the mechanics of writing a survey paper in data visualization or visual analytics. It serves as a useful starting point for those who have never written a survey paper or have very little experience. A literature review or survey paper is often considered the starting point of a PhD candidate's scientific degree. However, there are no dedicated papers that focus on guidelines for the planning or writing of a survey paper or literature review in visualization or visual analytics. We provide guidelines and our recommendations for a foundational structure on which to build a survey paper, whilst also considering intermediate goals, and offer helpful advice to improve the survey process and literature analysis. The result is a useful starting point for those wishing to write a survey paper or state-of-the-art (STAR) review in visualization or visual analytics. The guidelines and recommendations we make can also be generalized to other areas of computing and science. An abstract is a required feature of a survey paper and should identity the topic of the literature review. A good abstract addresses why the given topic is interesting and why it is helpful. A good abstract features the following elements: (1) topic introduction, (2) the motivation, (3) the goal of the review, and the benefits the review provides to the reader. A good literature survey offers a helpful classification of the literature, mature areas of research, and open, unsolved problems in visualization or visual analytics.
EUROGRAPHICS 2019: Tutorials Frontmatter
(Eurographics Association, 2019) Jakob, Wenzel; Puppo, Enrico; Jakob, Wenzel and Puppo, Enrico
Learning Generative Models of 3D Structures
(The Eurographics Association, 2019) Chaudhuri, Siddhartha; Ritchie, Daniel; Xu, Kai; Zhang, Hao (Richard); Jakob, Wenzel and Puppo, Enrico
Many important applications demand 3D content, yet 3D modeling is a notoriously difficult and inaccessible activity. This tutorial provides a crash course in one of the most promising approaches for democratizing 3D modeling: learning generative models of 3D structures. Such generative models typically describe a statistical distribution over a space of possible 3D shapes or 3D scenes, as well as a procedure for sampling new shapes or scenes from the distribution. To be useful by non-experts for design purposes, a generative model must represent 3D content at a high level of abstraction in which the user can express their goals-that is, it must be structure-aware. In this tutorial, we will take a deep dive into the most exciting methods for building generative models of both individual shapes as well as composite scenes, highlighting how standard data-driven methods need to be adapted, or new methods developed, to create models that are both generative and structure-aware. The tutorial assumes knowledge of the fundamentals of computer graphics, linear algebra, and probability, though a quick refresher of important algorithmic ideas from geometric analysis and machine learning is included. Attendees should come away from this tutorial with a broad understanding of the historical and current work in generative 3D modeling, as well as familiarity with the mathematical tools needed to start their own research or product development in this area.
Smoothed Particle Hydrodynamics Techniques for the Physics Based Simulation of Fluids and Solids
(The Eurographics Association, 2019) Koschier, Dan; Bender, Jan; Solenthaler, Barbara; Teschner, Matthias; Jakob, Wenzel and Puppo, Enrico
Graphics research on Smoothed Particle Hydrodynamics (SPH) has produced fantastic visual results that are unique across the board of research communities concerned with SPH simulations. Generally, the SPH formalism serves as a spatial discretization technique, commonly used for the numerical simulation of continuum mechanical problems such as the simulation of fluids, highly viscous materials, and deformable solids. Recent advances in the field have made it possible to efficiently simulate massive scenes with highly complex boundary geometries on a single PC [Com16b, Com16a]. Moreover, novel techniques allow to robustly handle interactions among various materials [Com18,Com17]. As of today, graphics-inspired pressure solvers, neighborhood search algorithms, boundary formulations, and other contributions often serve as core components in commercial software for animation purposes [Nex17] as well as in computer-aided engineering software [FIF16]. This tutorial covers various aspects of SPH simulations. Governing equations for mechanical phenomena and their SPH discretizations are discussed. Concepts and implementations of core components such as neighborhood search algorithms, pressure solvers, and boundary handling techniques are presented. Implementation hints for the realization of SPH solvers for fluids, elastic solids, and rigid bodies are given. The tutorial combines the introduction of theoretical concepts with the presentation of actual implementations.
Stylistic Locomotion Modeling with Conditional Variational Autoencoder
(The Eurographics Association, 2019) Du, Han; Herrmann, Erik; Sprenger, Janis; Cheema, Noshaba; hosseini, somayeh; Fischer, Klaus; Slusallek, Philipp; Cignoni, Paolo and Miguel, Eder
We propose a novel approach to create generative models for distinctive stylistic locomotion synthesis. The approach is inspired by the observation that human styles can be easily distinguished from a few examples. However, learning a generative model for natural human motions which display huge amounts of variations and randomness would require a lot of training data. Furthermore, it would require considerable efforts to create such a large motion database for each style. We propose a generative model to combine the large variation in a neutral motion database and style information from a limited number of examples. We formulate the stylistic motion modeling task as a conditional distribution learning problem. Style transfer is implicitly applied during the model learning process. A conditional variational autoencoder (CVAE) is applied to learn the distribution and stylistic examples are used as constraints. We demonstrate that our approach can generate any number of natural-looking human motions with a similar style to the target given a few style examples and a neutral motion database.
Area Lights in Signed Distance Function Scenes
(The Eurographics Association, 2019) Bán, Róbert; Bálint, Csaba; Valasek, Gábor; Cignoni, Paolo and Miguel, Eder
This paper presents two algorithms to incorporate spherical and general area lights into scenes defined by signed distance functions. The first algorithm employs an efficient approximation to the contribution of spherical lights to direct illumination and renders them at real-time rates. The second algorithm is of superior quality at a higher computational cost which is better suited for interactive rates. Our results are compared to both real-time soft shadow algorithms and a ground truth obtained by Monte Carlo integration. We show in these comparisons that our real-time solution computes more accurate shadows while the more demanding variant outperforms Monte Carlo integration at the expense of accuracy.
Towards Point-based Facial Movement Simulation
(The Eurographics Association, 2019) Uhlmann, Tom; Brunnett, Guido; Fusiello, Andrea and Bimber, Oliver
Lifelike animated characters are hard to create and involve extensive manual effort during generation of the geometry, adding a rig to the model, and creating the actual movements of limbs and tissue. Blendshapes is the leading technique regarding facial animations. This very simple mathematical model can be computed efficiently, thus it is suited for real time visualization. On the other hand it is hard to control, requires a skilled animator, and is still very error prone. Point-based simulation techniques became increasingly popular in recent years for animation of elastic surfaces, but have barely been used for facial animation. We argue, that this kind of technique is much more suited for simulation and animation of the non-rigid deformations of facial tissue. We build our proposal on a meshless finite elements technique, which has already been used successfully for the elastic simulation of surface models in real time and describe extensions to the approach so it can be applied for facial animation.
Planar Abstraction and Inverse Rendering of 3D Indoor Environment
(The Eurographics Association, 2019) Kim, Young Min; Ryu, Sangwoo; Kim, Ig-Jae; Cignoni, Paolo and Miguel, Eder
A large-scale scanned 3D environment suffers from complex occlusions and misalignment errors. The reconstruction contains holes in geometry and ghosting in texture. These are easily noticed and cannot be used in visually compelling VR content without further processing. On the other hand, the well-known Manhattan World priors successfully recreate relatively simple or clean structures. In this paper, we would like to push the limit of planar representation in indoor environments. We use planes not only to represent the environment geometrically but also to solve an inverse rendering problem considering texture and light. The complex process of shape inference and intrinsic imaging is greatly simplified with the help of detected planes and yet produces a realistic 3D indoor environment. The produced content can effectively represent the spatial arrangements for various AR/VR applications and can be readily combined with virtual objects possessing plausible lighting and texture.
A Parser-based Tool to Assist Instructors in Grading Computer Graphics Assignments
(The Eurographics Association, 2019) Andujar, Carlos; Raluca Vijulie, Cristina; Vinacua, Alvar; Tarini, Marco and Galin, Eric
Although online e-learning environments are increasingly used in university courses, manual assessment still dominates the way students are graded. Interactive judges providing a pass/fail verdict based on test sets are valuable tools both for learning and assessment, but still rely on human review of the code for output-independent issues such as readability and efficiency. In this paper we present a tool to assist instructors in grading programming exercises in Computer Graphics (CG) courses. In contrast to other grading solutions, assessment is based both on checking the output against test sets, and through a set of instructor-defined rubrics based on syntax analysis of the source code. Our current prototype runs in Python and supports the assessment of shaders written in GLSL language. We tested the tool in a CG course involving more than one hundred Computer Science students per year. Our first experiments show the tool can be useful to support both self-assessment and grading, as well as detecting grading mistakes through anomaly detection techniques based on features extracted from the syntax analysis.
Adaptive Frameless Rendering with NVIDIA OptiX
(The Eurographics Association, 2019) Hsiao, Chung-Che; Watson, Benjamin; Fusiello, Andrea and Bimber, Oliver
We implement adaptive frameless rendering (AFR) on NVIDIA OptiX, a real-time ray tracing API taking advantage of NVIDIA GPUs including their latest RTX functionality. OptiX is a parallel system that sits on top of NVIDIA's better-known CUDA API. AFR has sampling and reconstruction processes that use information distributed across both space and time, aiming to generate low-latency updates. Previous AFR implementations were sequential prototypes. Our parallel prototype is allowing us to confront several unique challenges, including closed loop control of both sampling and reconstruction, and load balancing between CPU and GPU.
Fine-Grained Semantic Segmentation of Motion Capture Data using Dilated Temporal Fully-Convolutional Networks
(The Eurographics Association, 2019) Cheema, Noshaba; hosseini, somayeh; Sprenger, Janis; Herrmann, Erik; Du, Han; Fischer, Klaus; Slusallek, Philipp; Cignoni, Paolo and Miguel, Eder
Human motion capture data has been widely used in data-driven character animation. In order to generate realistic, naturallooking motions, most data-driven approaches require considerable efforts of pre-processing, including motion segmentation and annotation. Existing (semi-) automatic solutions either require hand-crafted features for motion segmentation or do not produce the semantic annotations required for motion synthesis and building large-scale motion databases. In addition, human labeled annotation data suffers from inter- and intra-labeler inconsistencies by design. We propose a semi-automatic framework for semantic segmentation of motion capture data based on supervised machine learning techniques. It first transforms a motion capture sequence into a ''motion image'' and applies a convolutional neural network for image segmentation. Dilated temporal convolutions enable the extraction of temporal information from a large receptive field. Our model outperforms two state-of-the-art models for action segmentation, as well as a popular network for sequence modeling. Most of all, our method is very robust under noisy and inaccurate training labels and thus can handle human errors during the labeling process.
3DVFX: 3D Video Editing using Non-Rigid Structure-from-Motion
(The Eurographics Association, 2019) parashar, shaifali; Bartoli, Adrien; Cignoni, Paolo and Miguel, Eder
Numerous video post-processing techniques can add or remove objects to the observed scene in the video. Most of these techniques rely on 2D image points to perform the desired changes. Structure-from-Motion (SfM) has allowed the use of 3D points, however only for the objects that remain rigid in the scene. We propose to use both 2D image points and 3D points to modify the scene's deformable objects using Non-Rigid Structure-from-Motion (NRSfM). We rely on a recent effective NRSfM solution to develop a complete pipeline including manual 3D editing of an image and automatic 3D transfer of the edits. We perform object manipulation tasks such as retexturing a real deforming object.
Teaching Computer Graphics Based on a Commercial Product
(The Eurographics Association, 2019) Smith, Gregory; Sung, Kelvin; Tarini, Marco and Galin, Eric
The challenges in designing an introductory Computer Graphics (CG) course include selecting an appropriate and coherent set of topics, keeping up-to-date with the rapidly evolving industry, and aligning with the many students' fascinations that tend to stem from flashy popular media. This paper analyzes and classifies existing introductory CG classes according to their approaches in trading-off between covering foundation algorithms and focusing on application-level knowledge. The paper then observes that many application-level courses challenge students in learning and applying relevant CG concepts by building familiar graphical applications. Within this context, the paper points out that many modern commercial graphical applications, including popular game engines and 3D modeling systems, support well-defined and robust run-time scripting interfaces that allow modification and/or replacement of default system functional modules. These observations suggest the potentials of delivering an introductory CG class based on one of these commercial graphical systems. This paper proposes a set of guidelines to ensure such a class will educate CG practitioners rather than commercial product users. Based on these guidelines and an existing application-based introductory CG course, a new set of learning outcomes is derived which is independent of any specific commercial product. The paper continues to describe the implementation of a new course using the Unity3D game engine as the delivery vehicle. This paper then describes the associated teaching materials, details the hands-on programming assignments, and discusses student learning from the Unity3D-based introductory CG class. The results from two consecutive batches of students demonstrated that a commercial graphical product-based approach to teaching an introductory CG class could be effective, welcomed by students, and supply students the concepts to build practical graphical applications after the class.
3D Mesh Description Using ''Subdivided Shape-Curvature-Graphs''
(The Eurographics Association, 2019) Beguet, Florian; Guise, Jacques De; Schmittbuhl, Matthieu; Mari, Jean-Luc; Cresson, Thierry; Fusiello, Andrea and Bimber, Oliver
This paper presents a shape descriptor for 3D meshes using a graph to represent a polyhedral mesh which is then used to extract patterns from the shape. The use of Subdivided Shape-Curvature-Graphs makes it possible to not only recognize the similarities of mesh details but also determine the self-similarity of local portions of the object by adding topological information to the graph. The proposed method divides the mesh into 8 categories of patches using the discrete curvatures. These patches are cleaned; afterwards, to add topological information, a new "segmentation" patch is added. Finally, an approach is developed to extract and compare the subgraphs and thus be able to obtain the self-similarity of local parts of the mesh.
Visual Analytics for Epidemiology
(The Eurographics Association, 2019) Preim, Bernhard; Alemzadeh, Shiva; Ittermann, Till; Klemm, Paul; Niemann, Uli; Spiliopoulou, Myra; Bruckner, Stefan and Oeltze-Jafra, Steffen
We present visual analytics methods to analyze epidemiologic cohort studies. We consider the automatic identification of strong correlations and of subgroups that deviate from the global mean with respect to their risk for health disorders. Moreover, we tackle missing value problems and discuss appropriate imputation strategies and visual analytics support.
EUROGRAPHICS 2019: Posters Frontmatter
(Eurographics Association, 2019) Fusiello, Andrea; Bimber, Oliver; Fusiello, Andrea and Bimber, Oliver
One-step Compact Skeletonization
(The Eurographics Association, 2019) Durix, Bastien; Morin, Geraldine; Chambon, Sylvie; Mari, Jean-Luc; Leonard, Kathryn; Cignoni, Paolo and Miguel, Eder
Computing a skeleton for a discretized boundary typically produces a noisy output, with a skeletal branch produced for each boundary pixel. A simplification step often follows to reduce these noisy branches. As a result, generating a clean skeleton is usually a 2-step process. In this article, we propose a skeletonization process that produces a clean skeleton in the first step, avoiding the creation of branches due to noise. The resulting skeleton compares favorably with the most common pruning methods on a large database of shapes. Our process also reduces execution time and requires only one parameter, e, that designates the desired boundary precision in the Hausdorff distance.

Browse

Browsing EG2019 by Issue Date

Results Per Page

Sort Options