EG2023

Permanent URI for this community

https://diglib.eg.org/handle/10.2312/2633296

Browse

Now showing 1 - 20 of 45

Multi-Display Ray Tracing Framework
(The Eurographics Association, 2023) Romero Calla, Luciano Arnaldo; Mohanto, Bipul; Pajarola, Renato; Staadt, Oliver; Singh, Gurprit; Chu, Mengyu (Rachel)
We present a framework that will provide a highly efficient and scalable multi-display ray-tracing based rendering system capable of utilizing multiple GPU devices to produce high-quality images. Our system integrates advanced technologies, including MPI, CUDA, CUDA IPC, OptiX 7.6, and C++, resulting in a cutting-edge solution for interactive rendering.
A Survey on Discrete Laplacians for General Polygonal Meshes
(The Eurographics Association and John Wiley & Sons Ltd., 2023) Bunge, Astrid; Botsch, Mario; Bousseau, Adrien; Theobalt, Christian
The Laplace Beltrami operator is one of the essential tools in geometric processing. It allows us to solve numerous partial differential equations on discrete surface meshes, which is a fundamental building block in many computer graphics applications. Discrete Laplacians are typically limited to standard elements like triangles or quadrilaterals, which severely constrains the tessellation of the mesh. But in recent years, several approaches were able to generalize the Laplace Beltrami and its closely related gradient and divergence operators to more general meshes. This allows artists and engineers to work with a wider range of elements which are sometimes required and beneficial in their field. This paper discusses the different constructions of these three ubiquitous differential operators on arbitrary polygons and analyzes their individual advantages and properties in common computer graphics applications.
State of the Art in Dense Monocular Non-Rigid 3D Reconstruction
(The Eurographics Association and John Wiley & Sons Ltd., 2023) Tretschk, Edith; Kairanda, Navami; B R, Mallikarjun; Dabral, Rishabh; Kortylewski, Adam; Egger, Bernhard; Habermann, Marc; Fua, Pascal; Theobalt, Christian; Golyanik, Vladislav; Bousseau, Adrien; Theobalt, Christian
3D reconstruction of deformable (or non-rigid) scenes from a set of monocular 2D image observations is a long-standing and actively researched area of computer vision and graphics. It is an ill-posed inverse problem, since-without additional prior assumptions-it permits infinitely many solutions leading to accurate projection to the input 2D images. Non-rigid reconstruction is a foundational building block for downstream applications like robotics, AR/VR, or visual content creation. The key advantage of using monocular cameras is their omnipresence and availability to the end users as well as their ease of use compared to more sophisticated camera set-ups such as stereo or multi-view systems. This survey focuses on state-of-the-art methods for dense non-rigid 3D reconstruction of various deformable objects and composite scenes from monocular videos or sets of monocular views. It reviews the fundamentals of 3D reconstruction and deformation modeling from 2D image observations. We then start from general methods-that handle arbitrary scenes and make only a few prior assumptions-and proceed towards techniques making stronger assumptions about the observed objects and types of deformations (e.g. human faces, bodies, hands, and animals). A significant part of this STAR is also devoted to classification and a high-level comparison of the methods, as well as an overview of the datasets for training and evaluation of the discussed techniques. We conclude by discussing open challenges in the field and the social aspects associated with the usage of the reviewed methods.
Draw-Cut-Glue: Comparison of Paper House Model Creation in VR and on Paper in a Museum Education Programme - Pilot Study
(The Eurographics Association, 2023) Malý, Ivo; Vachková, Iva; Sedlácek, David; Magana, Alejandra; Zara, Jiri
In this paper, we describe the integration of Virtual Reality (VR) into a museum education programme. The aim of the programme is to present the cultural heritage of Langweil's model of Prague in the context of author's life in the 19th century. For the programme, we developed a VR application in which students experience the creation of Langweil's model of Prague, more specifically, they virtually draw and cut out a facade of a house and insert it into the rest of the model. As part of the educational programme, the students also experience a similar activity with a paper model, which leads them to compare the creation in VR and in reality with real tools. The context of the author's life is covered by two additional programme activities using a budget simulation and a discussion using historical photographs. In a pilot study we evaluated the programme with 31 students and we describe the observed results from both the students' and the organisation's perspectives.
Luminance-Preserving and Temporally Stable Daltonization
(The Eurographics Association, 2023) Ebelin, Pontus; Crassin, Cyril; Denes, Gyorgy; Oskarsson, Magnus; Åström, Kalle; Akenine-Möller, Tomas; Babaei, Vahid; Skouras, Melina
We propose a novel, real-time algorithm for recoloring images to improve the experience for a color vision deficient observer. The output is temporally stable and preserves luminance, the most important visual cue. It runs in 0.2 ms per frame on a GPU.
EUROGRAPHICS 2023: Posters Frontmatter
(Eurographics Association, 2023) Singh, Gurprit; Chu, Mengyu (Rachel); Singh, Gurprit; Chu, Mengyu (Rachel)
Out-of-the-loop Autotuning of Metropolis Light Transport with Reciprocal Probability Binning
(The Eurographics Association, 2023) Herveau, Killian; Otsu, Hisanari; Dachsbacher, Carsten; Babaei, Vahid; Skouras, Melina
The performance of Markov Chain Monte Carlo (MCMC) rendering methods depends heavily on the mutation strategies and their parameters. We treat the underlying mutation strategies as black-boxes and focus on their parameters. This avoids the need for tedious manual parameter tuning and enables automatic adaptation to the actual scene. We propose a framework for out-of-the-loop autotuning of these parameters. As a pilot example, we demonstrate our tuning strategy for small-step mutations in Primary Sample Space Metropolis Light Transport. Our σ-binning strategy introduces a set of mutation parameters chosen by a heuristic: the inverse probability of the local direction sampling, which captures some characteristics of the local sampling. We show that our approach can successfully control the parameters and achieve better performance compared to non-adaptive mutation strategies.
Radiance-Based Blender Add-On for Physically Accurate Rendering of Cultural Heritage
(The Eurographics Association, 2023) Méndez, Míriam; Munoz-Pandiella, Imanol; Andujar, Carlos; Singh, Gurprit; Chu, Mengyu (Rachel)
Despite the Cultural Heritage and Computer Graphics communities are increasingly joining forces to strengthen their collaboration, the study of how light interacts with monuments (e.g. weathering the surfaces or affecting the visitors' experience) is still an open problem in cultural heritage. A significant limitation is the lack of easy-to-use, open-source, physically-accurate tools allowing cultural heritage experts to perform lighting simulations on the increasing collection of 3D reconstructions. In this work, we present an open-source Blender add-on to facilitate such simulations. The add-on allows art historians to configure the properties (materials, lights, and camera) of the simulation, and uses as rendering back-end the Radiance software, a validated physically accurate light simulation tool. Our tool lowers the entry barrier for the use of a highly accurate but rather complex (command-based) tool for lighting studies in cultural heritage monuments.
Learning with Music Signals: Technology Meets Education
(The Eurographics Association, 2023) Müller, Meinard; Serrano, Ana; Slusallek, Philipp
Music information retrieval (MIR) is an exciting and challenging research area that aims to develop techniques and tools for organizing, analyzing, retrieving, and presenting music-related data. Being at the intersection of engineering and humanities, MIR relates to different research disciplines, including signal processing, machine learning, information retrieval, musicology, and the digital humanities. In this tutorial, using music as a tangible and concrete application domain, we will approach the concept of learning from different angles, addressing technological and educational aspects. When talking about learning in an engineering context, one immediately thinks of data-driven techniques such as deep learning (DL), where computer-based systems are trained to extract complex features and hidden relationships from given examples. In this tutorial, we will introduce various music analysis and retrieval tasks, where we start with classical engineering approaches. We then show how such approaches may be rephrased or simulated by DL-based systems, thus indicating new avenues toward building more explainable and hybrid machine-learning systems by learning from the experience of traditional engineering approaches and integrating knowledge from the music domain. Beyond this technical perspective, another aim of this tutorial is to approach the concept of learning from an educational perspective. We argue that music, being an essential part of our lives that everyone feels connected to, yields an intuitive entry point to support education in technical disciplines. In this tutorial, we will show how music may serve as a vehicle to make learning in signal processing and machine learning an interactive pursuit. In this context, we will also introduce a novel collection of educational material for teaching and learning fundamentals of music processing (FMP). This collection, referred to as FMP notebooks (https://www.audiolabs-erlangen.de/FMP) can be used to study both theory and practice, generate educational material for lectures, and provide baseline implementations for many MIR tasks. The tutorial's novelty lies in how it presents a holistic approach to learning using music as a challenging and tangible application domain. In this way, the tutorial serves several purposes: it gives a gentle introduction to MIR while introducing a new software package for teaching and learning music processing, it highlights avenues for developing explainable machine-learning models, and it discusses how recent technology can be applied and communicated in interdisciplinary research and education.
EUROGRAPHICS 2023: Education Papers Frontmatter
(The Eurographics Association, 2023) Magana, Alejandra; Zara, Jiri; Magana, Alejandra; Zara, Jiri
Towards Immersive Visualization for Large Lectures: Opportunities, Challenges, and Possible Solutions
(The Eurographics Association, 2023) Popescu, Voicu; Magana, Alejandra J.; Benes, Bedrich; Magana, Alejandra; Zara, Jiri
In this position paper, we discuss deploying immersive visualization in large lectures (IVLL). We take the position that IVLL has great potential to benefit students and that, thanks to the current advances in computer hardware and software, IVLL implementation is now possible. We argue that IVLL is best done using mixed reality (MR) headsets, which, compared to virtual reality (VR) headsets, have the advantages of allowing students to see important elements of the real world and avoiding cybersickness. We argue that immersive visualization can be beneficial at any point on the student engagement continuum. We argue that immersive visualization allows reconfiguring large lectures dynamically, partitioning the class with great flexibility in groups of students of various sizes, or accommodating 3D visualizations of monumental size. We inventory the challenges that have to be overcome to implement IVLL, and we argue that they currently have acceptable solutions, opening the door to developing a first IVLL system.
Photogrammetric Reconstruction of a Stolen Statue
(The Eurographics Association, 2023) Liu, Zishun; Doubrovski, Eugeni L.; Geraedts, Jo M. P.; Wang, Wenting; Yam, Yeung; Wang, Charlie C. L.; Babaei, Vahid; Skouras, Melina
In this paper, we propose a method to reconstruct a digital 3D model of a stolen/damaged statue using photogrammetric methods. This task is challenging because the number of available photos for a stolen statue is in general very limited - especially the side/back view photos. Besides using standard structure-from-motion and multi-view stereo methods, we match image pairs with low overlap using sliding windows and maximize the normalized cross-correlation (NCC) based patch-consistency so that the image pairs can be well aligned into a complete model to build the 3D mesh surface. Our method is based on the prior of the planar side on the statue's pedestal, which can cover a large range of statues. We hope this work will motivate more research efforts for the reconstruction of those stolen/damaged statues and heritage preservation.
DropSPH: ISPH Simulation of Droplet Interactions with a Solid Surface
(The Eurographics Association, 2023) Keshtkar, Hossein; Aburumman, Nadine; Singh, Gurprit; Chu, Mengyu (Rachel)
We present a physically-based model to simulate droplet behaviours when impacted on a solid surface. Our model creates the coalescence, spreading, and break-up deformations that occur when a liquid droplet collides with a solid surface. We model the attraction-repulsion forces within an improved free surface Incompressible Smoothed Particle Hydrodynamics (ISPH) framework that includes contact force and cohesion force between particles. The results show that our model is effective in simulating several small-scale liquid phenomena.
Modern High Dynamic Range Imaging at the Time of Deep Learning
(The Eurographics Association, 2023) Banterle, Francesco; Artusi, Alessandro; Serrano, Ana; Slusallek, Philipp
In this tutorial, we introduce how the High Dynamic Range (HDR) imaging field has evolved in this new era where machine learning approaches have become dominant. The main reason of this success is that the use of machine learning and deep learning have automatized many tedious tasks achieving high-quality results overperforming classic methods. After an introduction on classic HDR imaging and its open problem, we will summarize the main approaches for: merging of multiple exposures, single image reconstructions or inverse tone mapping, tone mapping, and display visualization. Finally, we will highlights the still open problems in this machine learning era, and possible direction on how to solve them.
Is Drawing Order Important?
(The Eurographics Association, 2023) Qiu, Sherry; Wang, Zeyu; McMillan, Leonard; Rushmeier, Holly; Dorsey, Julie; Babaei, Vahid; Skouras, Melina
The drawing process is crucial to understanding the final result of a drawing. There has been a long history of understanding human drawing; what kinds of strokes people use and where they are placed. An area of interest in Artificial Intelligence is developing systems that simulate human behavior in drawing. However, there has been little work done to understand the order of strokes in the drawing process. Without sufficient understanding of natural drawing order, it is difficult to build models that can generate natural drawing processes. In this paper, we present a study comparing multiple types of stroke orders to confirm findings from previous work and demonstrate that multiple orderings of the same set of strokes can be perceived as human-drawn and different stroke order types achieve different perceived naturalness depending on the type of image prompt.
Velocity-Based LOD Reduction in Virtual Reality: A Psychophysical Approach
(The Eurographics Association, 2023) Petrescu, David; Warren, Paul A.; Montazeri, Zahra; Pettifer, Steve; Babaei, Vahid; Skouras, Melina
Virtual Reality headsets enable users to explore the environment by performing self-induced movements. The retinal velocity produced by such motion reduces the visual system's ability to resolve fine detail. We measured the impact of self-induced head rotations on the ability to detect quality changes of a realistic 3D model in an immersive virtual reality environment. We varied the Level of Detail (LOD) as a function of rotational head velocity with different degrees of severity. Using a psychophysical method, we asked 17 participants to identify which of the two presented intervals contained the higher quality model under two different maximum velocity conditions. After fitting psychometric functions to data relating the percentage of correct responses to the aggressiveness of LOD manipulations, we identified the threshold severity for which participants could reliably (75%) detect the lower LOD model. Participants accepted an approximately four-fold LOD reduction even in the low maximum velocity condition without a significant impact on perceived quality, suggesting that there is considerable potential for optimisation when users are moving (increased range of perceptual uncertainty). Moreover, LOD could be degraded significantly more (around 84%) in the maximum head velocity condition, suggesting these effects are indeed speed-dependent.
EUROGRAPHICS 2023: Short Papers Frontmatter
(Eurographics Association, 2023) Babaei, Vahid; Skouras, Melina; Babaei, Vahid; Skouras, Melina
A Comprehensive Review of Data-Driven Co-Speech Gesture Generation
(The Eurographics Association and John Wiley & Sons Ltd., 2023) Nyatsanga, Simbarashe; Kucherenko, Taras; Ahuja, Chaitanya; Henter, Gustav Eje; Neff, Michael; Bousseau, Adrien; Theobalt, Christian
Gestures that accompany speech are an essential part of natural and efficient embodied human communication. The automatic generation of such co-speech gestures is a long-standing problem in computer animation and is considered an enabling technology for creating believable characters in film, games, and virtual social spaces, as well as for interaction with social robots. The problem is made challenging by the idiosyncratic and non-periodic nature of human co-speech gesture motion, and by the great diversity of communicative functions that gestures encompass. The field of gesture generation has seen surging interest in the last few years, owing to the emergence of more and larger datasets of human gesture motion, combined with strides in deep-learning-based generative models that benefit from the growing availability of data. This review article summarizes co-speech gesture generation research, with a particular focus on deep generative models. First, we articulate the theory describing human gesticulation and how it complements speech. Next, we briefly discuss rule-based and classical statistical gesture synthesis, before delving into deep learning approaches. We employ the choice of input modalities as an organizing principle, examining systems that generate gestures from audio, text and non-linguistic input. Concurrent with the exposition of deep learning approaches, we chronicle the evolution of the related training data sets in terms of size, diversity, motion quality, and collection method (e.g., optical motion capture or pose estimation from video). Finally, we identify key research challenges in gesture generation, including data availability and quality; producing human-like motion; grounding the gesture in the co-occurring speech in interaction with other speakers, and in the environment; performing gesture evaluation; and integration of gesture synthesis into applications. We highlight recent approaches to tackling the various key challenges, as well as the limitations of these approaches, and point toward areas of future development.
Synthetic Dataset for Panic Detection in Human Crowded Scenes
(The Eurographics Association, 2023) Calle, Javier; Leskovsky, Peter; Garcia, Jorge; Sanchez, Marti; Singh, Gurprit; Chu, Mengyu (Rachel)
AI is increasingly being used in public protection by using crowd anomaly detection. This is useful for identifying panic events enabling control forces to act faster. A significant challenge in this field is the lack of data for training these algorithms. Recreating panic events with big crowds can be both expensive and hazardous. To address this issue, this paper proposes the creation of a synthetic dataset for crowd panic behaviour. The process involves defining the scenario and setting up the appropriate CCTV cameras. Many scenarios are prepared, including variations in weather conditions. Next is the scene population with pedestrians and vehicles, with different crowd sizes and vehicle trajectories. To recreate panic, the behaviour of each person is programmed. The final videos show normality situations before the panic events start. Finally, we achieved 1717 simulations.
Tight Bounding Boxes for Voxels and Bricks in a Signed Distance Field Ray Tracer
(The Eurographics Association, 2023) Hansson-Söderlund, Herman; Akenine-Möller, Tomas; Babaei, Vahid; Skouras, Melina
We present simple methods to compute tight axis-aligned bounding boxes for voxels and for bricks of voxels in a signed distance function renderer based on ray tracing. Our results show total frame time reductions of 20-31% in a real-time path tracer.

Browse

Browsing EG2023 by Issue Date

Results Per Page

Sort Options