EG2020

Permanent URI for this community

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

Browse

Now showing 1 - 20 of 50

Accelerated Foveated Rendering based on Adaptive Tessellation
(The Eurographics Association, 2020) Tiwary, Ankur; Ramanathan, Muthuganapathy; Kosinka, Jiri; Wilkie, Alexander and Banterle, Francesco
We propose an optimization method for adaptive geometric tessellation, involving the saccadic motion of the human eye and foveated rendering. Increased demands on computational resources, especially in the field of head-mounted devices with gaze contingency make optimization schemes pertinent for a seamless user experience. For implementing foveated rendering, our algorithm tessellates a 3D model in real-time based on the location of the user's gaze, substituted with a mouse cursor in this project as a proof of concept. Saccades and fixations of the human eye are simulated by delaying the process of tessellation and rendering by the minimum time taken to complete a saccade. Calculations required for tessellation and rendering the changes on the screen are stalled as and when the eye fixates after a saccade. The paper walks through our contribution by describing the theory, the application method, and results from our user study evaluating our method.
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.
Asset Integration: An Exceptional Undergraduate Student Project
(The Eurographics Association, 2020) Redford, Adam; Romero, Mario and Sousa Santos, Beatrice
This paper outlines an exceptional 1st year undergraduate student project that involves the creation of a CG asset (goblet), and the integration of that asset into a live action photographed background. The final created shot of the animated asset shows a high level of photo-realism, and is an exceptionally close match to the live action reference photography of the real goblet.
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.
Compression and Real-Time Rendering of Inward Looking Spherical Light Fields
(The Eurographics Association, 2020) Hajisharif, Saghi; Miandji, Ehsan; Baravadish, Gabriel; Larsson, Per; Unger, Jonas; Wilkie, Alexander and Banterle, Francesco
Photorealistic rendering is an essential tool for immersive virtual reality. In this regard, the data structure of choice is typically light fields since they contain multidimensional information about the captured environment that can provide motion parallax and view-dependent information such as highlights. There are various ways to acquire light fields depending on the nature of the scene, limitations on the capturing setup, and the application at hand. Our focus in this paper is on full-parallax imaging of large-scale static objects for photorealistic real-time rendering. To this end, we introduce and simulate a new design for capturing inward-looking spherical light fields, and propose a system for efficient compression and real-time rendering of such data using consumer-level hardware suitable for virtual reality applications.
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.
Controllable Caustic Animation Using Vector Fields
(The Eurographics Association, 2020) Rojo, Irene Baeza; Gross, Markus; Günther, Tobias; Wilkie, Alexander and Banterle, Francesco
In movie production, lighting is commonly used to redirect attention or to set the mood in a scene. The detailed editing of complex lighting phenomena, however, is as tedious as it is important, especially with dynamic lights or when light is a relevant story element. In this paper, we propose a new method to create caustic animations, which are controllable through constraints drawn by the user. Our method blends caustics into a specified target image by treating photons as particles that move in a divergence-free fluid, an irrotational vector field or a linear combination of the two. Once described as a flow, additional user constraints are easily added, e.g., to direct the flow, create boundaries or add synthetic turbulence, which offers new ways to redirect and control light. The corresponding vector field is computed by fitting a stream function and a scalar potential per time step, for which constraints are described in a quadratic energy that we minimize as a linear least squares problem. Finally, photons are placed at their new positions back into the scene and are rendered with progressive photon mapping.
Critical Thinking Sheet (CTS) for Design Thinking in Programming Courses
(The Eurographics Association, 2020) Roberts, Jonathan C.; Ritsos, Panagiotis D.; Romero, Mario and Sousa Santos, Beatrice
We present a quick design process, which encourages learners to sketch their design, reflect on the main algorithm and consider how to implement it. In-depth design processes have their advantages, but often are not practical within the time given to the student, and may not fit the learning outcomes of the module. Without any planning students often jump into coding without contemplating what they will do, leading to failure or poor design. Our single-sheet method, allows the learners to critically think of the challenge and decompose the problem into several subproblems (the appearance, functionality and algorithmic steps of the solution). We have successfully used this technique for three years in a second year computer graphics module, for undergraduate degree students studying Computer Science. We present our method, explain how we use it with second year computer graphics students, and discuss student's experiences with the method
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.
Designing a Course on Non-Photorealistic Rendering
(The Eurographics Association, 2020) Ilinkin, Ivaylo; Romero, Mario and Sousa Santos, Beatrice
This paper presents a course design on Non-Photorealistic Rendering (NPAR). As a sub-field of computer graphics, NPAR aims to model artistic media, styles, and techniques that capture salient characteristics in images to convey particular information or mood. The results can be just as inspiring as the photorealistic scenes produced with the latest ray-tracing techniques even though the goals are fundamentally different. The paper offers ideas for developing a full course on NPAR by presenting a series of assignments that cover a wide range of NPAR techniques and shares experience on teaching such a course at the junior/senior undergraduate level.
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.
EUROGRAPHICS 2020: CGF 39-2 STARs Frontmatter
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Mantiuk, Rafal; Sundstedt, Veronica; Mantiuk, Rafal and Sundstedt, Veronica
-
EUROGRAPHICS 2020: Education Papers Frontmatter
(Eurographics Association, 2020) Romero, Mario; Sousa Santos, Beatrice; Romero, Mario and Sousa Santos, Beatrice
EUROGRAPHICS 2020: Posters Frontmatter
(Eurographics Association, 2020) Ritschel, Tobias; Eilertsen, Gabriel; Ritschel, Tobias and Eilertsen, Gabriel
EUROGRAPHICS 2020: Short Papers Frontmatter
(Eurographics Association, 2020) Wilkie, Alexander; Banterle, Francesco; Wilkie, Alexander and Banterle, Francesco
EUROGRAPHICS 2020: Tutorials Frontmatter
(Eurographics Association, 2020) Fjeld, Morten; Frisvad, Jeppe Revall; Fjeld, Morten and Frisvad, Jeppe Revall
Fabric Appearance Benchmark
(The Eurographics Association, 2020) Merzbach, Sebastian; Klein, Reinhard; Ritschel, Tobias and Eilertsen, Gabriel
Appearance modeling is a difficult problem that still receives considerable attention from the graphics and vision communities. Though recent years have brought a growing number of high-quality material databases that have sparked new research, there is a general lack of evaluation benchmarks for performance assessment and fair comparisons between competing works. We therefore release a new dataset and pose a public challenge that will enable standardized evaluations. For this we measured 56 fabric samples with a commercial appearance scanner. We publish the resulting calibrated HDR images, along with baseline SVBRDF fits. The challenge is to recreate, under known light and view sampling, the appearance of a subset of unseen images. User submissions will be automatically evaluated and ranked by a set of standard image metrics.
First Order Signed Distance Fields
(The Eurographics Association, 2020) Bán, Róbert; Valasek, Gábor; Wilkie, Alexander and Banterle, Francesco
This paper investigates a first order generalization of signed distance fields. We show that we can improve accuracy and storage efficiency by incorporating the spatial derivatives of the signed distance function into the distance field samples. We show that a representation in power basis remains invariant under barycentric combination, as such, it is interpolated exactly by the GPU. Our construction is applicable in any geometric setting where point-surface distances can be queried. To emphasize the practical advantages of this approach, we apply our results to signed distance field generation from triangular meshes. We propose storage optimization approaches and offer a theoretical and empirical accuracy analysis of our proposed distance field type in relation to traditional, zero order distance fields. We show that the proposed representation may offer an order of magnitude improvement in storage while retaining the same precision as a higher resolution distance field.
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.
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.

Browse

Browsing EG2020 by Title

Results Per Page

Sort Options