EG 2019 - Short Papers
Permanent URI for this collection
Animation and Simulation
Perceptual Characteristics by Motion Style Category
] [
]
Hye Ji Kim and Sung-Hee Lee
GPU Smoke Simulation on Compressed DCT Space
Daichi Ishida, Ryoichi Ando, and Shigeo Morishima
Stylistic Locomotion Modeling with Conditional Variational Autoencoder
Han Du, Erik Herrmann, Janis Sprenger, Noshaba Cheema, Somayeh Hosseini, Klaus Fischer, and
Philipp Slusallek
Geometry Processing
Schelling Meshes
Luther Power and Manfred Lau
Hybrid Function Representation with Distance Properties
Alexander Tereshin, Valery Adzhiev, Oleg Fryazinov, and Alexander Pasko
One-step Compact Skeletonization
Bastien Durix, Geraldine Morin, Sylvie Chambon, Jean-Luc Mari, and Kathryn Leonard
A Preliminary Analysis of Methods for Curvature Estimation on Surfaces With Local Reliefs
Elia Moscoso Thompson and Silvia Biasotti
Image and Video
3DVFX: 3D Video Editing using Non-Rigid Structure-from-Motion
Shaifali Parashar and Adrien Bartoli
Image Recoloring Based on Object Color Distributions
Mahmoud Afifi, Brian Price, Scott Cohen, and Michael S. Brown
Making Gabor Noise Fast and Normalized
Vincent Tavernier, Fabrice Neyret, Romain Vergne, and Joëlle Thollot
Automatic Environment Map Registration
Ulysse Larvy, Céline Loscos, and Yiorgos Chrysanthou
Interactivity and Gaming
Investigating Different Augmented Reality Approaches in Circuit Assembly: a User Study
Bernardo Marques, Rafael Esteves, João Alves, Carlos Ferreira, Paulo Dias, and Beatriz
Sousa Santos
Integrating Server-based Simulations Into Web-based Geo-applications
Pascal Bormann, Ralf Gutbell, Johannes Sebastian Mueller-Roemer
Asteroid Escape: A Serious Game to Foster Teamwork Abilities
Filippo Gabriele Pratticó, Francesco Strada, Fabrizio Lamberti, and Andrea Bottino
Learning and Networks
A Validation Tool For Improving Semantic Segmentation of Complex Natural Structures
Gaia Pavoni, Massimiliano Corsini, Marco Palma, and Roberto Scopigno
Font Specificity
Luther Power and Manfred Lau
Towards Diverse Anime Face Generation: Active Label Completion and Style Feature Network
Hongyu Li and Tianqi Han
Fine-Grained Semantic Segmentation of Motion Capture Data using Dilated Temporal
Fully-Convolutional Networks
Cheema Noshaba, Somayeh Hosseini, Janis Sprenger, Erik Herrmann, Han Du, Klaus Fischer, and
Philipp Slusallek
Rendering
Optimal Deterministic Mixture Sampling
Mateu Sbert, Vlastimil Havran, and László Szirmay-Kalos
Anisotropic Filtering for On-the-fly Patch-based Texturing
Nicolas Lutz, Basile Sauvage, Frédéric Larue, and Jean-Michel Dischler
Planar Abstraction and Inverse Rendering of 3D Indoor Environment
Young Min Kim, Sangwoo Ryu, and Ig-Jae Kim
Area Lights in Signed Distance Function Scenes
Róbert Bán, Csaba Bálint, and Gábor Valasek
Browse
Recent Submissions
Item Perceptual Characteristics by Motion Style Category(The Eurographics Association, 2019) Kim, Hye Ji; Lee, Sung-Hee; Cignoni, Paolo and Miguel, EderMotion style is important as it characterizes a motion by expressing the context of the motion such as emotion and personality. Yet, the perception and interpretation of motion styles is subjective and may vary greatly from person to person. This paper investigates the perceptual characteristics of motion styles for a wide range of styles. After categorizing the motion styles, we perform user studies to examine the diversity of interpretations of motion styles and the association level between style motions and their corresponding text descriptions. Our study shows that motion styles have different interpretation diversity and association level according to their categories. We discuss the implications of these findings and recommend a method of labeling or describing motion styles.Item GPU Smoke Simulation on Compressed DCT Space(The Eurographics Association, 2019) Ishida, Daichi; Ando, Ryoichi; Morishima, Shigeo; Cignoni, Paolo and Miguel, EderThis paper presents a novel GPU-based algorithm for smoke animation. Our primary contribution is the use of Discrete Cosine Transform (DCT) compressed space for efficient simulation. We show that our method runs an order of magnitude faster than a CPU implementation while retaining visual details with a smaller memory usage. The key component of our method is an on-the-fly compression and expansion of velocity, pressure and density fields. Whenever these physical quantities are requested during a simulation, we perform data expansion and compression only where necessary in a loop. As a consequence, our simulation allows us to simulate a large domain without actually allocating full memory space for it. We show that albeit our method comes with some extra cost for DCT manipulations, such cost can be minimized with the aid of a devised shared memory usage.Item 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, EderWe 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.Item Schelling Meshes(The Eurographics Association, 2019) Power, Luther; Lau, Manfred; Cignoni, Paolo and Miguel, EderThe concept of ''Schelling points'' on 3D shapes has been explored for points on the surface of a 3D mesh. In this paper, we introduce the notion of ''Schelling meshes'' which extends the Schelling concept to 3D meshes as a whole themselves. We collect Schelling-based data for meshes where participants are given a group of shapes and asked to choose those with the aim of matching with what they expect others to choose. We analyze the data by computing the Schelling frequency of each shape and characterizing the qualitative features that make a shape ''Schelling''. We show that the Schelling frequencies can be learned and demonstrate Schelling-guided shape applications.Item Hybrid Function Representation with Distance Properties(The Eurographics Association, 2019) Tereshin, Alexander; Adzhiev, Valery; Fryazinov, Oleg; Pasko, Alexander; Cignoni, Paolo and Miguel, EderThis paper describes a novel framework allowing for a hybrid representation of heterogeneous objects. We consider advantages and drawbacks of the conventional representations based on scalar fields of different kinds. The main result is introducing a hybrid representation called Hybrid Function Representation (HFRep) that preserves the advantages of the Function Representation (FRep) and Signed Distance Fields (SDFs) without their drawbacks. This new representation allows for obtaining a continuous smooth distance field in the Euclidean space for the FRep. We present the mathematical basics for our approach that uses the Discrete Distance Transform (DDT) and a step-function. The procedure for generation HFRep using continuous interpolation and smoothing techniques are also described. A few examples show how the approach works in practice.Item One-step Compact Skeletonization(The Eurographics Association, 2019) Durix, Bastien; Morin, Geraldine; Chambon, Sylvie; Mari, Jean-Luc; Leonard, Kathryn; Cignoni, Paolo and Miguel, EderComputing 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.Item A Preliminary Analysis of Methods for Curvature Estimation on Surfaces With Local Reliefs(The Eurographics Association, 2019) Moscoso Thompson, Elia; Biasotti, Silvia; Cignoni, Paolo and Miguel, EderCurvature estimation is very popular in geometry processing for the analysis of local surface variations. Despite the large number of methods, no quantitative nor qualitative studies have been conducted for a comparative analysis of the different algorithms on surfaces with small geometric variations, such as chiselled or relief surfaces. In this work we compare eight curvature estimation methods that are commonly adopted by the computer graphics community on a number of triangle meshes derived from scans of surfaces with local reliefs.Item 3DVFX: 3D Video Editing using Non-Rigid Structure-from-Motion(The Eurographics Association, 2019) parashar, shaifali; Bartoli, Adrien; Cignoni, Paolo and Miguel, EderNumerous 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.Item Image Recoloring Based on Object Color Distributions(The Eurographics Association, 2019) Afifi, Mahmoud; Price, Brian; Cohen, Scott; Brown, Michael S.; Cignoni, Paolo and Miguel, EderWe present a method to perform automatic image recoloring based on the distribution of colors associated with objects present in an image. For example, when recoloring an image containing a sky object, our method incorporates the observation that objects of class 'sky' have a color distribution with three dominant modes for blue (daytime), yellow/red (dusk/dawn), and dark (nighttime). Our work leverages recent deep-learning methods that can perform reasonably accurate object-level segmentation. By using the images in datasets used to train deep-learning object segmentation methods, we are able to model the color distribution of each object class in the dataset. Given a new input image and its associated semantic segmentation (i.e., object mask), we perform color transfer to map the input image color histogram to a set of target color histograms that were constructed based on the learned color distribution of the objects in the image. We show that our framework is able to produce compelling color variations that are often more interesting and unique than results produced by existing methods.Item Automatic Environment Map Registration(The Eurographics Association, 2019) Larvy, Ulysse; Loscos, Céline; Chrysanthou, Yiorgos; Cignoni, Paolo and Miguel, EderIn this paper, a method to automatically register an environment map (EM) around a local scene is presented. In the literature, this step is most of the time manually processed by a user. However, it is an essential step when lighting and/or background coherence is needed. We present a method to find the coherent spatial organization between a main light source present in the EM and a couple object/shadow in a local scene. We automatically recover the EM orientation which corresponds to the local scene illumination. We proceed to a 3D representation of the scene using the EM mapped on a hemisphere as a background scene, a simplified geometry description of the reference object and its shadow outline. As a first step, we compute a projection of the main object shadow to compare it against the real acquired shadow. In a second step, we minimize a metric based on Euclidean Distance Transform (EDT), to compare both shadows and to recover the EM orientation. We demonstrate that we can automatically find rotation and scaling parameters that position in a coherent manner the background around a local scene.Item Making Gabor Noise Fast and Normalized(The Eurographics Association, 2019) Tavernier, Vincent; Neyret, Fabrice; Vergne, Romain; Thollot, Joëlle; Cignoni, Paolo and Miguel, EderGabor Noise is a powerful procedural texture synthesis technique, but it has two major drawbacks: It is costly due to the high required splat density and not always predictable because properties of instances can differ from those of the process. We bench performance and quality using alternatives for each Gabor Noise ingredient: point distribution, kernel weighting and kernel shape. For this, we introduce 3 objective criteria to measure process convergence, process stationarity, and instance stationarity. We show that minor implementation changes allow for 17-24x speed-up with same or better quality.Item Investigating Different Augmented Reality Approaches in Circuit Assembly: a User Study(The Eurographics Association, 2019) Marques, Bernardo; Esteves, Rafael; Alves, João; Ferreira, Carlos; Dias, Paulo; Santos, Beatriz Sousa; Cignoni, Paolo and Miguel, EderAugmented Reality (AR) has been considered as having great potential in assisting performance and training of complex tasks. Assembling electronic circuits is such a task, since many errors may occur, as wrong choice or positioning of components or incorrect wiring and thus using AR approaches may be beneficial. This paper describes a controlled experiment aimed at comparing usability and acceptance of two AR-based approaches (one based on a single device and another approach using two interconnected devices), with a traditional approach using a paper manual in the assembly of an electronic circuit. Participants were significantly faster and made fewer errors while using the AR approaches, and most preferred the multi-device approach.Item Integrating Server-based Simulations Into Web-based Geo-applications(The Eurographics Association, 2019) Bormann, Pascal; Gutbell, Ralf; Mueller-Roemer, Johannes Sebastian; Cignoni, Paolo and Miguel, EderIn this work, we present a novel approach for combining fluid simulations running on a GPU server with terrain rendered by a web-based 3D GIS system. We introduce a hybrid rendering approach, combining server-side and client-side rendering, to interactively display the results of a shallow water simulation on client devices using web technology. To display water and terrain in unison, we utilize image merging based on depth values.We extend it to deal with numerical and compression artifacts as well as Level-of-detail rendering and use Depth Image Based Rendering to counteract network latency.Item Asteroid Escape: A Serious Game to Foster Teamwork Abilities(The Eurographics Association, 2019) Pratticò, Filippo Gabriele; Strada, Francesco; Lamberti, Fabrizio; Bottino, Andrea; Cignoni, Paolo and Miguel, EderTeamwork skills have become a fundamental asset in the labor market. Modern organizations are increasingly implementing team building activities, aimed to improve or assess their employees' skills. Research suggests that serious games could be promising tools capable to support the creation of engaging and effective team building experiences. However, the design and development of serious games targeting these activities is still sparse and requires further investigation. This work introduces Asteroid Escape, an immersive serious game for team building, whose design was based on theoretical models on teamwork effectiveness. Although conducted on a restricted user sample, preliminary experiments suggest that tools like the devised one could positively contribute to ongoing research and implementation efforts targeting the exploitation of technology-enhanced learning methods for the development of teamwork skills and, more in general, of so-called soft skills.Item Font Specificity(The Eurographics Association, 2019) Power, Luther; Lau, Manfred; Cignoni, Paolo and Miguel, EderWe explore the concept of ''image specificity'' for fonts and introduce the notion of ''font specificity''. The idea is that a font that elicits consistent descriptions from different people are more ''specific''. We collect specificity-based data for fonts where participants are given each font and asked to describe it with words. We then analyze the data and characterize the qualitative features that make a font ''specific''. Finally, we show that the notion of font specificity can be learned and demonstrate some specificity-guided applications.Item A Validation Tool For Improving Semantic Segmentation of Complex Natural Structures(The Eurographics Association, 2019) Pavoni, Gaia; Corsini, Massimiliano; Palma, Marco; Scopigno, Roberto; Cignoni, Paolo and Miguel, EderThe automatic recognition of natural structures is a challenging task in the supervised learning field. Complex morphologies are difficult to detect both from the networks, that may suffer from generalization issues, and from human operators, affecting the consistency of training datasets. The task of manual annotating biological structures is not comparable to a generic task of detecting an object (a car, a cat, or a flower) within an image. Biological structures are more similar to textures, and specimen borders exhibit intricate shapes. In this specific context, manual labelling is very sensitive to human error. The interactive validation of the predictions is a valuable resource to improve the network performance and address the inaccuracy caused by the lack of annotation consistency of human operators reported in literature. The proposed tool, inspired by the Yes/No Answer paradigm, integrates the semantic segmentation results coming from a CNN with the previous human labeling, allowing a more accurate annotation of thousands of instances in a short time. At the end of the validation, it is possible to obtain corrected statistics or export the integrated dataset and re-train the network.Item Towards Diverse Anime Face Generation: Active Label Completion and Style Feature Network(The Eurographics Association, 2019) Li, Hongyu; Han, Tianqi; Cignoni, Paolo and Miguel, EderIt is interesting to use an anime face as personal virtual image to replace the traditional sequence code. To generate diverse anime faces, this paper proposes a style-gender based anime GAN (SGA-GAN), where the gender is directly conditioned to ensure the gender differentiation, and style features serve as a condition to guarantee the style diversity. To extract style features, we train a style feature network (SFN) as a multi-task classifier to simultaneously fulfill gender classification, style classification, and image quality estimation. To make full use of available data, partly labeled or unlabeled, during the SFN training, we propose a label completion method to actively complete the missing gender or style labels. The active label completion is essentially a weakly-supervised learning process through ensembling three distinct classifiers to improve the generalization capability. Experiments verify that the active label completion can improve the model accuracy and the style feature as a condition can make better the diversity of generated anime faces.Item 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, EderHuman 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.Item Optimal Deterministic Mixture Sampling(The Eurographics Association, 2019) Sbert, Mateu; Havran, Vlastimil; Szirmay-Kalos, László; Cignoni, Paolo and Miguel, EderMultiple 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.Item Anisotropic Filtering for On-the-fly Patch-based Texturing(The Eurographics Association, 2019) Lutz, Nicolas; Sauvage, Basile; Larue, Frédéric; Dischler, Jean-Michel; Cignoni, Paolo and Miguel, EderOn-the-fly patch-based texturing consists of choosing at run-time, for several patches within a tileable texture, one random candidate among a pre-computed set of possible contents. This category of methods generates unbounded textures, for which filtering is not straightforward, because the screen pixel footprint may overlap multiple patches in texture space, i.e. different randomly chosen contents. In this paper, we propose a real-time anisotropic filtering which is fully compliant with the standard graphics pipeline. The main idea is to pre-filter the contents independently, store them in an atlas, and combine them at run-time to produce the final pixel color. The patch-map, referencing to which patch belong the fetched texels, requires a specific filtering approach, in order to recover the patches that overlap at low resolutions. In addition, we show how this method can achieve blending at patch boundaries in order to further reduce visible seams, without modification of our filtering algorithm.Item 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, EderA 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.Item Area Lights in Signed Distance Function Scenes(The Eurographics Association, 2019) Bán, Róbert; Bálint, Csaba; Valasek, Gábor; Cignoni, Paolo and Miguel, EderThis 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.Item EUROGRAPHICS 2019: Short Papers Frontmatter(Eurographics Association, 2019) Cignoni, Paolo; Miguel, Eder; Cignoni, Paolo and Miguel, Eder