EG2020

Permanent URI for this community

https://diglib.eg.org/handle/10.2312/2632883

Browse

Now showing 1 - 20 of 50

Adversarial Generation of Continuous Implicit Shape Representations
(The Eurographics Association, 2020) Kleineberg, Marian; Fey, Matthias; Weichert, Frank; Wilkie, Alexander and Banterle, Francesco
This work presents a generative adversarial architecture for generating three-dimensional shapes based on signed distance representations. While the deep generation of shapes has been mostly tackled by voxel and surface point cloud approaches, our generator learns to approximate the signed distance for any point in space given prior latent information. Although structurally similar to generative point cloud approaches, this formulation can be evaluated with arbitrary point density during inference, leading to fine-grained details in generated outputs. Furthermore, we study the effects of using either progressively growing voxel- or point-processing networks as discriminators, and propose a refinement scheme to strengthen the generator's capabilities in modeling the zero iso-surface decision boundary of shapes. We train our approach on the SHAPENET benchmark dataset and validate, both quantitatively and qualitatively, its performance in generating realistic 3D shapes.
From Perception to Interaction with Virtual Characters
(The Eurographics Association, 2020) Zell, Eduard; Zibrek, Katja; Pan, Xueni; Gillies, Marco; McDonnell, Rachel; Fjeld, Morten and Frisvad, Jeppe Revall
This course will introduce students, researchers and digital artists to the recent results in perceptual research on virtual characters. It covers how technical and artistic aspects that constitute the appearance of a virtual character influence human perception, and how to create a plausibility illusion in interactive scenarios with virtual characters. We will report results of studies that addressed the influence of low-level cues like facial proportions, shading or level of detail and higher-level cues such as behavior or artistic stylization. We will place emphasis on aspects that are encountered during character development, animation, interaction design and achieving consistency between the visuals and storytelling. We will close with the relationship between verbal and non-verbal interaction and introduce some concepts which are important for creating convincing character behavior in virtual reality. The insights that we present in this course will serve as an additional toolset to anticipate the effect of certain design decisions and to create more convincing characters, especially in the case where budgets or time are limited.
Treemap Literacy: A Classroom-Based Investigation
(The Eurographics Association, 2020) Firat, Elif E.; Denisova, Alena; Laramee, Robert S.; Romero, Mario and Sousa Santos, Beatrice
Visualization literacy, the ability to interpret and understand visual designs, has gained momentum in the educational and information visualization communities. The goal of this research is to identify and address barriers to treemap literacy - a popular visual design, with a view to improve a non-expert user's treemap visualization literacy skills. In this paper we present the results of two years of an information visualization assignment, which are used to identify the barriers to and challenges of understanding and creating treemaps. From this, we develop a treemap visualization literacy test. Then, we propose a pedagogical tool that facilitates both teaching and learning of treemaps and advances treemap visualization literacy. To investigate the efficiency of this educational software, we then conduct a classroom-based study with 25 participants. We identify the properties of treemaps that can hinder literacy and cognition based on the results from the treemap visualization literacy test. Results also provide further support for the use of our tool that had a positive effect on treemap literacy skills of university students.
Interactive Flat Coloring of Minimalist Neat Sketches
(The Eurographics Association, 2020) Parakkat, Amal Dev; Madipally, Prudhviraj; Gowtham, Hari Hara; Cani, Marie-Paule; Wilkie, Alexander and Banterle, Francesco
We introduce a simple Delaunay-triangulation based algorithm for the interactive coloring of neat line-art minimalist sketches, ie. vector sketches that may include open contours. The main objective is to minimize user intervention and make interaction as natural as with the flood-fill algorithm while extending coloring to regions with open contours. In particular, we want to save the user from worrying about parameters such as stroke weight and size. Our solution works in two steps, 1) a segmentation step in which the input sketch is automatically divided into regions based on the underlying Delaunay structure and 2) the interactive grouping of neighboring regions based on user input. More precisely, a region adjacency graph is computed from the segmentation result, and is interactively partitioned based on user input to generate the final colored sketch. Results show that our method is as natural as a bucket fill tool and powerful enough to color minimalist sketches.
EUROGRAPHICS 2020: Short Papers Frontmatter
(Eurographics Association, 2020) Wilkie, Alexander; Banterle, Francesco; Wilkie, Alexander and Banterle, Francesco
State of the Art on Neural Rendering
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Tewari, Ayush; Fried, Ohad; Thies, Justus; Sitzmann, Vincent; Lombardi, Stephen; Sunkavalli, Kalyan; Martin-Brualla, Ricardo; Simon, Tomas; Saragih, Jason; Nießner, Matthias; Pandey, Rohit; Fanello, Sean; Wetzstein, Gordon; Zhu, Jun-Yan; Theobalt, Christian; Agrawala, Maneesh; Shechtman, Eli; Goldman, Dan B.; Zollhöfer, Michael; Mantiuk, Rafal and Sundstedt, Veronica
Efficient rendering of photo-realistic virtual worlds is a long standing effort of computer graphics. Modern graphics techniques have succeeded in synthesizing photo-realistic images from hand-crafted scene representations. However, the automatic generation of shape, materials, lighting, and other aspects of scenes remains a challenging problem that, if solved, would make photo-realistic computer graphics more widely accessible. Concurrently, progress in computer vision and machine learning have given rise to a new approach to image synthesis and editing, namely deep generative models. Neural rendering is a new and rapidly emerging field that combines generative machine learning techniques with physical knowledge from computer graphics, e.g., by the integration of differentiable rendering into network training. With a plethora of applications in computer graphics and vision, neural rendering is poised to become a new area in the graphics community, yet no survey of this emerging field exists. This state-of-the-art report summarizes the recent trends and applications of neural rendering. We focus on approaches that combine classic computer graphics techniques with deep generative models to obtain controllable and photorealistic outputs. Starting with an overview of the underlying computer graphics and machine learning concepts, we discuss critical aspects of neural rendering approaches. Specifically, our emphasis is on the type of control, i.e., how the control is provided, which parts of the pipeline are learned, explicit vs. implicit control, generalization, and stochastic vs. deterministic synthesis. The second half of this state-of-the-art report is focused on the many important use cases for the described algorithms such as novel view synthesis, semantic photo manipulation, facial and body reenactment, relighting, free-viewpoint video, and the creation of photo-realistic avatars for virtual and augmented reality telepresence. Finally, we conclude with a discussion of the social implications of such technology and investigate open research problems.
Frequency-Aware Reconstruction of Fluid Simulations with Generative Networks
(The Eurographics Association, 2020) Biland, Simon; Azevedo, Vinicius C.; Kim, Byungsoo; Solenthaler, Barbara; Wilkie, Alexander and Banterle, Francesco
Convolutional neural networks were recently employed to fully reconstruct fluid simulation data from a set of reduced parameters. However, since (de-)convolutions traditionally trained with supervised l1-loss functions do not discriminate between low and high frequencies in the data, the error is not minimized efficiently for higher bands. This directly correlates with the quality of the perceived results, since missing high frequency details are easily noticeable. In this paper, we analyze the reconstruction quality of generative networks and present a frequency-aware loss function that is able to focus on specific bands of the dataset during training time. We show that our approach improves reconstruction quality of fluid simulation data in mid-frequency bands, yielding perceptually better results while requiring comparable training time.
Procedural 3D Asteroid Surface Detail Synthesis
(The Eurographics Association, 2020) Li, Xi-zhi; Weller, René; Zachmann, Gabriel; Wilkie, Alexander and Banterle, Francesco
We present a novel noise model to procedurally generate volumetric terrain on implicit surfaces. The main idea is to combine a novel Locally Controlled 3D Spot noise (LCSN) for authoring the macro structures and 3D Gabor noise to add micro details. More specifically, a spatially-defined kernel formulation in combination with an impulse distribution enables the LCSN to generate arbitrary size craters and boulders, while the Gabor noise generates stochastic Gaussian details. The corresponding metaball positions in the underlying implicit surface preserve locality to avoid the globality of traditional procedural noise textures, which yields an essential feature that is often missing in procedural texture based terrain generators. Furthermore, different noise-based primitives are integrated through operators, i.e. blending, replacing, or warping into the complex volumetric terrain. The result is a completely implicit representation and, as such, has the advantage of compactness as well as flexible user control. We applied our method to generating high quality asteroid meshes with fine surface details.
Space-Time Blending for Heterogeneous Objects
(The Eurographics Association, 2020) Tereshin, Alexander; Anderson, Eike; Pasko, Alexander; Adzhiev, Valery; Wilkie, Alexander and Banterle, Francesco
Space-time blending (STB) is an established technique allowing to implement a metamorphosis operation between geometric shapes. In this paper we significantly extend the STB method to make it possible to deal with heterogeneous objects, which are volumetric objects with attributes representing their physical properties. The STB method, used for geometry transformation, is naturally combined with space-time transfinite interpolation, used for attribute (e.g. colour) transformation. Geometry and attribute transformations are interconnected and happen simultaneously in an higher dimensional specific STB space. We use hybrid function representation, unifying function representation with signed distance fields and with adaptively sampled distance fields. We show how the new method works by applying it to 4D animated Cubism.
Triplanar Displacement Mapping for Terrain Rendering
(The Eurographics Association, 2020) Weiss, Sebastian; Bayer, Florian; Westermann, Rüdiger; Wilkie, Alexander and Banterle, Francesco
Heightmap-based terrain representations are common in computer games and simulations. However, adding geometric details to such a representation during rendering on the GPU is difficult to achieve. In this paper, we propose a combination of triplanar mapping, displacement mapping, and tessellation on the GPU, to create extruded geometry along steep faces of heightmap-based terrain fields on-the-fky during rendering. The method allows rendering geometric details such as overhangs and boulders, without explicit triangulation. We further demonstrate how to handle collisions and shadows for the enriched geometry.
Recreating Past and Present: An Exceptional Student-Created Virtual Heritage Experience
(The Eurographics Association, 2020) Anderson, Eike Falk; Sloan, Susan; Romero, Mario and Sousa Santos, Beatrice
We present an outstanding undergraduate student project in the form of a virtual heritage experience, created by a multidisciplinary group of six 4th semester undergraduate students from a range of computer graphics related programmes of study, ranging from 3D art and design to graphics software development. The "Exercise Smash" application allows participants to take part in a 1944 military exercise that was held in preparation of the D-Day landings in Normandy, during which several amphibious tanks sank, and then to dive down to the tank wrecks on the modern-day seafloor. The virtual heritage experience was presented during a public event at a military history museum and has also been demonstrated at an archaeology conference, being well-received in both cases.
Learning Body Shape and Pose from Dense Correspondences
(The Eurographics Association, 2020) Yoshiyasu, Yusuke; Gamez, Lucas; Wilkie, Alexander and Banterle, Francesco
In this paper, we address the problem of learning 3D human pose and body shape from 2D image dataset, without having to use 3D supervisions (body shape and pose) which are in practice difficult to obtain. The idea is to use dense correspondences between image points and a body surface, which can be annotated on in-the-wild 2D images, to extract, aggregate and learn 3D information such as body shape and pose from them. To do so, we propose a training strategy called "deform-and-learn" where we alternate deformable surface registration and training of deep convolutional neural networks (ConvNets). Experimental results showed that our method is comparable to previous semi-supervised techniques that use 3D supervision.
A Survey on Sketch Based Content Creation: from the Desktop to Virtual and Augmented Reality
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Bhattacharjee, Sukanya; Chaudhuri, Parag; Mantiuk, Rafal and Sundstedt, Veronica
Sketching is one of the most natural ways for representing any object pictorially. It is however, challenging to convert sketches to 3D content that is suitable for various applications like movies, games and computer aided design. With the advent of more accessible Virtual Reality (VR) and Augmented Reality (AR) technologies, sketching can potentially become a more powerful yet easy-to-use modality for content creation. In this state-of-the-art report, we aim to present a comprehensive overview of techniques related to sketch based content creation, both on the desktop and in VR/AR. We discuss various basic concepts related to static and dynamic content creation using sketches. We provide a structured review of various aspects of content creation including model generation, coloring and texturing, and finally animation. We try to motivate the advantages that VR/AR based sketching techniques and systems can offer into making sketch based content creation a more accessible and powerful mode of expression. We also discuss and highlight various unsolved challenges that current sketch based techniques face with the goal of encouraging future research in the domain.
Pair Correlation Functions with Free-Form Boundaries for Distribution Inpainting and Decomposition
(The Eurographics Association, 2020) Nicolet, Baptiste; Ecormier-Nocca, Pierre; Memari, Pooran; Cani, Marie-Paule; Wilkie, Alexander and Banterle, Francesco
Pair Correlation Functions (PCF) have been recently spreading as a reliable representation for distributions, enabling the efficient synthesis of point-sets, vector textures and object placement from examples. In this work we introduce a triangulationbased local filtering method to extend PCF-based analysis to exemplars with free-form boundaries. This makes PCF applicable to new problems such as the inpainting of missing parts in an input distribution, or the decomposition of complex, non-homogeneous distributions into a set of coherent classes, in which each category of points can be studied together with their intra and inter-class correlations.
Black Box Geometric Computing with Python: From Theory to Practice
(The Eurographics Association, 2020) Koch, Sebastian; Schneider, Teseo; Li, Chengchen; Panozzo, Daniele; Fjeld, Morten and Frisvad, Jeppe Revall
The first part of the course is theoretical, and introduces the finite element method trough interactive Jupyter notebooks. It also covers recent advancements toward an integrated pipeline, considering meshing and element design as a single challenge, leading to a black box pipeline that can solve simulations on ten thousand in the wild meshes, without any parameter tuning. In the second part we will move to practice, introducing a set of easy-to-use Python packages for applications in geometric computing. The presentation will have the form of live coding in a Jupyter notebook. We have designed the presented libraries to have a shallow learning curve, while also enabling programmers to easily accomplish a wide variety of complex tasks. Furthermore, these libraries utilize NumPy arrays as a common interface, making them highly composable with each-other as well as existing scientific computing packages. Finally, our libraries are blazing fast, doing most of the heavy computations in C++ with a minimal constant-overhead interface to Python. In the course, we will present a set of real-world examples from geometry processing, physical simulation, and geometric deep learning. Each example is prototypical of a common task in research or industry and is implemented in a few lines of code. By the end of the course, attendees will have exposure to a swiss-army-knife of simple, composable, and high-performance tools for geometric computing.
Organic Narrative Charts
(The Eurographics Association, 2020) Bolte, Fabian; Bruckner, Stefan; Wilkie, Alexander and Banterle, Francesco
Storyline visualizations display the interactions of groups and entities and their development over time. Existing approaches have successfully adopted the general layout from hand-drawn illustrations to automatically create similar depictions. Ward Shelley is the author of several diagrammatic paintings that show the timeline of art-related subjects, such as Downtown Body, a history of art scenes. His drawings include many stylistic elements that are not covered by existing storyline visualizations, like links between entities, splits and merges of streams, and tags or labels to describe the individual elements. We present a visualization method that provides a visual mapping for the complex relationships in the data, creates a layout for their display, and adopts a similar styling of elements to imitate the artistic appeal of such illustrations.We compare our results to the original drawings and provide an open-source authoring tool prototype.
Deep-Eyes: Fully Automatic Anime Character Colorization with Painting of Details on Empty Pupils
(The Eurographics Association, 2020) Akita, Kenta; Morimoto, Yuki; Tsuruno, Reiji; Wilkie, Alexander and Banterle, Francesco
Many studies have recently applied deep learning to the automatic colorization of line drawings. However, it is difficult to paint empty pupils using existing methods because the networks are trained with pupils that have edges, which are generated from color images using image processing. Most actual line drawings have empty pupils that artists must paint in. In this paper, we propose a novel network model that transfers the pupil details in a reference color image to input line drawings with empty pupils. We also propose a method for accurately and automatically coloring eyes. In this method, eye patches are extracted from a reference color image and automatically added to an input line drawing as color hints using our eye position estimation network.
An End-to-end Framework for 3D Capture and Human Digitization with a Single RGB Camera
(The Eurographics Association, 2020) Silva, Luiz José Schirmer; Silva, Djalma S. da; Velho, Luiz; Lopes, Hélio; Ritschel, Tobias and Eilertsen, Gabriel
We present a low cost and accessible end-to-end framework for 3D modeling and texture capture of Humans using deep neural networks and a single RGB camera. We generate a texture atlas considering a set of multi-view images. We also capture data to generate 3D shape models and finally combine it with the generated textures to obtain a full 3D reconstruction of the human body that can be used in a game engine.
Conservative Ray Batching using Geometry Proxies
(The Eurographics Association, 2020) Molenaar, Mathijs; Eisemann, Elmar; Wilkie, Alexander and Banterle, Francesco
We present a method for improving batched ray traversal as was presented by Pharr et al. [PKGH97]. We propose to use conservative proxy geometry to more accurately determine whether a ray has a possibility of hitting any geometry that is stored on disk. This prevents unnecessary disk loads and thus reduces the disk bandwidth.
A Survey of Temporal Antialiasing Techniques
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Yang, Lei; Liu, Shiqiu; Salvi, Marco; Mantiuk, Rafal and Sundstedt, Veronica
Temporal Antialiasing (TAA), formally defined as temporally-amortized supersampling, is the most widely used antialiasing technique in today's real-time renderers and game engines. This survey provides a systematic overview of this technique. We first review the history of TAA, its development path and related work. We then identify the two main sub-components of TAA, sample accumulation and history validation, and discuss algorithmic and implementation options. As temporal upsampling is becoming increasingly relevant to today's game engines, we propose an extension of our TAA formulation to cover a variety of temporal upsampling techniques. Despite the popularity of TAA, there are still significant unresolved technical challenges that affect image quality in many scenarios. We provide an in-depth analysis of these challenges, and review existing techniques for improvements. Finally, we summarize popular algorithms and topics that are closely related to TAA. We believe the rapid advances in those areas may either benefit from or feedback into TAA research and development.

Browse

Browsing EG2020 by Issue Date

Results Per Page

Sort Options