EG2018

Permanent URI for this community

https://diglib.eg.org/handle/10.2312/2632158

Browse

Now showing 1 - 20 of 57

Kinder-Gator: The UF Kinect Database of Child and Adult Motion
(The Eurographics Association, 2018) Aloba, Aishat; Flores, Gianne; Woodward, Julia; Shaw, Alex; Castonguay, Amanda; Cuba, Isabella; Dong, Yuzhu; Jain, Eakta; Anthony, Lisa; Diamanti, Olga and Vaxman, Amir
Research has suggested that children's whole-body motions are different from those of adults. However, research on children's motions, and how these motions differ from those of adults, is limited. One possible reason for this limited research is that there are few motion capture (mocap) datasets for children, with most datasets focusing on adults instead. There are even fewer datasets that have both children's and adults' motions to allow for comparison between them. To address these problems, we present Kinder-Gator, a new dataset of ten children and ten adults performing whole-body motions in front of the Kinect v1.0. The data contains RGB and 3D joint positions for 58 motions, such as wave, walk in place, kick, and point, which have been manually labeled according to the category of the participant (child vs. adult), and the motion being performed. We believe this dataset will be useful in supporting research and applications in animation and whole-body motion recognition and interaction.
EUROGRAPHICS 2018: Posters Frontmatter
(Eurographics Association, 2018) Jain, Eakta; Kosinka, Jirí; Jain, Eakta; Kosinka, Jirí
State of the Art on Monocular 3D Face Reconstruction, Tracking, and Applications
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Zollhöfer, Michael; Thies, Justus; Garrido, Pablo; Bradley, Derek; Beeler, Thabo; Pérez, Patrick; Stamminger, Marc; Nießner, Matthias; Theobalt, Christian; Hildebrandt, Klaus and Theobalt, Christian
The computer graphics and vision communities have dedicated long standing efforts in building computerized tools for reconstructing, tracking, and analyzing human faces based on visual input. Over the past years rapid progress has been made, which led to novel and powerful algorithms that obtain impressive results even in the very challenging case of reconstruction from a single RGB or RGB-D camera. The range of applications is vast and steadily growing as these technologies are further improving in speed, accuracy, and ease of use. Motivated by this rapid progress, this state-of-the-art report summarizes recent trends in monocular facial performance capture and discusses its applications, which range from performance-based animation to real-time facial reenactment. We focus our discussion on methods where the central task is to recover and track a three dimensional model of the human face using optimization-based reconstruction algorithms. We provide an in-depth overview of the underlying concepts of real-world image formation, and we discuss common assumptions and simplifications that make these algorithms practical. In addition, we extensively cover the priors that are used to better constrain the under-constrained monocular reconstruction problem, and discuss the optimization techniques that are employed to recover dense, photo-geometric 3D face models from monocular 2D data. Finally, we discuss a variety of use cases for the reviewed algorithms in the context of motion capture, facial animation, as well as image and video editing.
Expressive Curve Editing with the Sigma Lognormal Model
(The Eurographics Association, 2018) Berio, Daniel; Leymarie, Frederic Fol; Plamondon, Réjean; Diamanti, Olga and Vaxman, Amir
We describe a practical application of the Sigma Lognormal model of handwriting movements for computer graphics applications that require the interactive or procedural definition of artistic or calligraphic traces. The method allows to easily edit curves with physiologically plausible kinematics that can be exploited in order to generate expressive brush renderings, natural looking stroke animations and easily generate stylistic variations of a trace.
Human Sensitivity to Light Zones in Virtual Scenes
(The Eurographics Association, 2018) Kartashova, Tatiana; Ridder, Huib de; Pas, Susan F. te; Pont, Sylvia C.; Jain, Eakta and Kosinka, Jirí
We investigated perception of light properties in scenes containing volumes with dramatically different light properties (direction, intensity, diffuseness). Each scene had two light zones, defined as distinct spatial groupings of lighting variables significant to the space- and form-giving characteristics of light [Mad07]. The results show that human observers are more sensitive to differences in illumination between two parts of a scene when the differences occur in the picture plane than in depth of the scene. We discuss implications for and possible applications of our results in computer graphics.
A Preliminary Investigation into the Impact of Training for Example-Based Facial Blendshape Creation
(The Eurographics Association, 2018) Carrigan, Emma; Hoyet, Ludovic; McDonnell, Rachel; Avril, Quentin; Diamanti, Olga and Vaxman, Amir
Our work is a perceptual study into the effects of training poses on the Example-Based Facial Rigging (EBFR) method. We analyse the output of EBFR given a set of training poses to see how well the results reproduced our ground truth actor scans compared to a Deformation Transfer approach. While EBFR produced better results overall, there were cases that did not see any improvement. While some of these results may be explained by lack of sufficient training poses for the area of the face in question, we found that certain lip poses were not improved by training, despite a large number of mouth training poses supplied.
Teaching Spatial Augmented Reality: a Practical Assignment for Large Audiences
(The Eurographics Association, 2018) Ridel, Brett; Reuter, Patrick; Couture, Nadine; Post, Frits and Žára, Jirí
We present a new methodology to teach spatial augmented reality in a practical assignment to large audiences. Our approach does not require specific equipment such as video projectors while teaching the principal topics and difficulties involved in spatial augmented reality applications, and especially calibration and tracking. The key idea is to set up a scene graph consisting of a 3D scene with a simulated projector that "projects" content onto a virtual representation of the real-world object. For illustrating the calibration, we simplify the intrinsic parameters to using the field of view, both for the camera and the projector. For illustrating the tracking, instead of relying on specific hardware or software, we exploit the relative transformations in the scene graph. We implemented our teaching methodology in Unity3D and tested it within a three-hour assignment to 24 and 20 master-level students in two consecutive years. We show the positive feedback that we received and discuss our plans for further improvement.
Light Field Synthesis from a Single Image using Improved Wasserstein Generative Adversarial Network
(The Eurographics Association, 2018) Ruan, Lingyan; Chen, Bin; Lam, Miu Ling; Jain, Eakta and Kosinka, Jirí
We present a deep learning-based method to synthesize a 4D light field from a single 2D RGB image. We consider the light field synthesis problem equivalent to image super-resolution, and solve it by using the improved Wasserstein Generative Adversarial Network with gradient penalty (WGAN-GP). Experimental results demonstrate that our algorithm can predict complex occlusions and relative depths in challenging scenes. The light fields synthesized by our method has much higher signal-to-noise ratio and structural similarity than the state-of-the-art approach.
GL-Socket: A CG Plugin-based Framework for Teaching and Assessment
(The Eurographics Association, 2018) Andujar, Carlos; Chica, Antonio; Fairén, Marta; Vinacua, Alvar; Post, Frits and Žára, Jirí
In this paper we describe a plugin-based C++ framework for teaching OpenGL and GLSL in introductory Computer Graphics courses. The main strength of the framework architecture is that student assignments are mostly independent and thus can be completed, tested and evaluated in any order. When students complete a task, the plugin interface forces a clear separation of initialization, interaction and drawing code, which in turn facilitates code reusability. Plugin code can access scene, camera, and OpenGL window methods through a simple API. The plugin interface is flexible enough to allow students to complete tasks requiring shader development, object drawing, and multiple rendering passes. Students are provided with sample plugins with basic scene drawing and camera control features. One of the plugins that the students receive contains a shader development framework with self-assessment features. We describe the lessons learned after using the tool for four years in a Computer Graphics course involving more than one hundred Computer Science students per year.
Raw Point Cloud Deferred Shading Through Screen Space Pyramidal Operators
(The Eurographics Association, 2018) Bouchiba, Hassan; Deschaud, Jean-Emmanuel; Goulette, François; Diamanti, Olga and Vaxman, Amir
We present a novel real-time raw point cloud rendering algorithm based on efficient screen-space pyramidal operators. Our method is based on a pyramidal occlusion-based hidden point removal operator followed by a pyramidal reconstruction by the pull push algorithm. Then a new pyramidal smooth normals estimator enables subsequent deferred shading. We demonstrate on various real-world complex objects and scenes that our method achieves better visual results and is one order of magnitude more efficient comparing to state of the art algorithms.
Time-Reversed Art Directable Smoke Simulation
(The Eurographics Association, 2018) Oborn, Jeremy; Flynn, Sean; Egbert, Parris; Holladay, Seth; Diamanti, Olga and Vaxman, Amir
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 address a number of challenges associated with time-reversal including the problem of decreasing entropy.
Understanding Mystery Behind Example-Based Image Synthesis
(The Eurographics Association, 2018) Lu, J.; Lukác, M.; Sýkora, Daniel; Ritschel, Tobias and Telea, Alexandru
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 completion, retargeting, reshuffling, morphing, melding, painting by feature, appearance transfer to fluid animations or artistic style transfer to 3D models and facial animations.
Turtle Fractals and Spirolaterals: Effective Assignments for Novice Graphics Programmers
(The Eurographics Association, 2018) Anderson, Eike Falk; Post, Frits and Žára, Jirí
This paper presents an effective assignment in the shape of a computer graphics application from an introductory computing course with a graphics programming flavour. The assignment involves basic 2D computer graphics used in combination with fundamental algorithmic elements to create a simple drawing application. Students are first asked to create a data structure and appropriate functions replicating the operations of a Turtle graphics system and then to use this turtle for drawing either fractals or spirolateral curves.
Smoothing Noisy Skeleton Data in Real Time
(The Eurographics Association, 2018) Hoxey, Thomas; Stephenson, Ian; Jain, Eakta and Kosinka, Jirí
The aim of this project is to be able to visualise live skeleton tracking data in a virtual analogue of a real world environment, to be viewed in VR. Using a single RGBD camera motion tracking method is a cost effective way to get real time 3D skeleton tracking data. Not only this but people being tracked don't need any special markers. This makes it much more practical for use in a non studio or lab environment. However the skeleton it provides is not as accurate as a traditional multiple camera system. With a single fixed view point the body can easily occlude itself, for example by standing side on to the camera. Secondly without marked tracking points there can be inconsistencies with where the joints are identified, leading to inconsistent body proportions. In this paper we outline a method for improving the quality of motion capture data in real time, providing an off the shelf framework for importing the data into a virtual scene. Our method uses a two stage approach to smooth smaller inconsistencies and try to estimate the position of improperly proportioned or occluded joints.
Reduction of CPU-GPU Synchronization Overhead for Accelerating Implicit Clothing Simulator
(The Eurographics Association, 2018) Lee, Sangbin; Ryu, Donghan; Ko, Hyeong-Seok; Diamanti, Olga and Vaxman, Amir
When trying to make the conjugate gradient (CG) method exploit GPU technology, this paper notes that the communication between CPU and GPU to transfer the residual value and waiting for the CPU's decision whether to continue further iterations is a new source of delay that has been overlooked and turns out not negligible. By examining the residual decrease pattern in log scale, this paper proposes so-called the Secant Lazy Residual Evaluation (Secant LRE) method to skip needless synchronization. We experimented the method for a clothing simulator and found that the proposed method reduces the sync overhead significantly, leading to 10 60% performance gain.
Towards Self-Perception in Augmented Virtuality: Hand Segmentation with Fully Convolutional Networks
(The Eurographics Association, 2018) Gonzalez-Sosa, Ester; Perez, Pablo; Kachach, Redouane; Ruiz, Jaime Jesus; Villegas, Alvaro; Jain, Eakta and Kosinka, Jirí
In this work, we propose the use of deep learning techniques to segment items of interest from the local region to increase self-presence in Virtual Reality (VR) scenarios. Our goal is to segment hand images from the perspective of a user wearing a VR headset. We create the VR Hand Dataset, composed of more than 10:000 images, including variations of hand position, scenario, outfits, sleeve and people. We also describe the procedure followed to automatically generate groundtruth images and create synthetic images. Preliminary results look promising.
Smooth Blended Subdivision Shading
(The Eurographics Association, 2018) Bakker, Jelle; Barendrecht, Pieter J.; Kosinka, Jiri; Diamanti, Olga and Vaxman, Amir
The concept known as subdivision shading aims at improving the shading of subdivision surfaces. It is based on the subdivision of normal vectors associated with the control net of the surface. By either using the resulting subdivided normal field directly, or blending it with the normal field of the limit surface, renderings of higher visual smoothness can be obtained. In this work we propose a different and more versatile approach to blend the two normal fields, yielding not only better results, but also a proof that our blended normal field is C1.
Image-Based Information Visualization Tutorial
(The Eurographics Association, 2018) Hurter, Christophe; Ritschel, Tobias and Telea, Alexandru
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 requirements.
A Comparison of GPU Tessellation Strategies for Multisided Patches
(The Eurographics Association, 2018) Hettinga, Gerben Jan; Barendrecht, Pieter J.; Kosinka, Jiri; Diamanti, Olga and Vaxman, Amir
We propose an augmentation of the traditional tessellation pipeline with several different strategies that efficiently render multisided patches using generalised barycentric coordinates. The strategies involve different subdivision steps and the usage of textures. In addition, we show that adaptive tessellation techniques naturally extend to some of these strategies whereas others need a slight adjustment. The technique of Loop et al. [LSNC09], commonly known as ACC-2, is extended to multisided faces to illustrate the effectiveness of multisided techniques. A performance and quality comparison is made between the different strategies and remarks on the techniques and implementation details are provided.
I3T: Using Interactive Computer Graphics to Teach Geometric Transformations
(The Eurographics Association, 2018) Felkel, Petr; Magana, Alejandra J.; Folta, Michal; Sears, Alexa Gabrielle; Benes, Bedrich; Post, Frits and Žára, Jirí
Geometric transformations play an important role in a vast variety of disciplines. Although they belong to the fundamental concepts, they are also difficult to comprehend. Thousands of students take courses of algebra every year and although they may conceptually understand the transformations and mechanically solve the presented problems, they often struggle in visualizing the effect of the transformation on 3D objects represented as matrices. We explored the hypothesis that using interactive 3D computer graphics to visualize the transformations has its learning benefit.We have developed a novel framework for interactive 3D transformations called Interactive 3D Transformations (I3T) that allows for exploring and visualizing immediate effect of 3D transformations on rigid objects. We tested nine graduate students with I3T and compared them with the control group of another nine participants that used traditional passive methods. Moreover, we have tested the students spatial abilities by using a standardized test and we have evaluated how this affects their ability to comprehend the 3D transformations. Overall results showed that students increased their understanding of transformations between the pretest and posttest in both groups. When comparing the two groups, although the mean score in the posttest was two times higher for the I3T group, it did not show that this was statistically significantly higher than for the Traditional Group. The written responses showed higher enthusiasm of the students who used the interactive tool as opposed to using the passive learning method.

Browse

Browsing EG2018 by Issue Date

Results Per Page

Sort Options