Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
Exploring Perceptual Homogenization through a VR-Based AI Narrative
No full textThis research explores how the drive for cognitive efficiency in Artificial Intelligence (AI) may contribute to the homogenization of sensory experiences. We present Abstract.exe, a Virtual Reality (VR) installation designed as a critical medium for this inquiry. The experience places participants in a detailed virtual forest where their exploration triggers an AI-driven ''simplification'' of the world. Visuals, models, and lighting progressively degrade, aiming to transform the 3D scene into abstract 2D color fields. This work attempts to translate the abstract logic of AI-driven summarization into a tangible, immersive experience. This paper outlines the concept and technical implementation in Unreal Engine 5 (UE5), which utilizes a Procedural Content Generation (PCG) framework. Abstract.exe is intended as both an artistic inquiry and a cautionary exploration of how we might preserve experiential richness in an algorithmically influenced world.Pacific Graphics Conference Papers, Posters, and DemosPosters and Demo
Gaze-Aware Visualisation: Design Considerations and Research Agenda
No full textEye tracking provides a unique perspective on the inherently visual discourse between visualisation systems and their users, and has recently become sufficiently precise and affordable to be integrated as regular input into workstations and virtual or augmented reality headsets alike. As such, real-time eye tracking can now contribute significantly towards the development of gaze-aware visualisations that infer and monitor users' needs to actively support their activities. To facilitate such systems we make three contributions. First, we structure and discuss design considerations for gaze-aware visualisations along four axes: measurable data; inferable data; opportunities for support; and limiting factors to beware. Second, we distill visualisation research challenges that preclude such systems. Finally, we show via three usage scenarios how to apply these design considerations to imagine how existing systems can benefit from real-time eye tracking. We combined a structured literature analysis, a consideration of suitable places for eye-tracking integration in the typical visualisation ecosystem, and design space modelling. Eye tracking has significant potential to improve the interactive visual analysis of data across many visualisation domains. Our paper attempts to provide a comprehensive, general survey and conceptual discussion in this promising field, outlining the state-of-the-art and future research opportunities.Computer Graphics ForumOriginal Article44
A Graph Layout Evaluation System for Communication Graphs
No full textCommunication networks are a type of graph that occurs in different areas such as robotic, Internet of Things, and general network communication. Layouting such networks for visualization is an ongoing research task, while already existing layout algorithms are plenty and allow for broad parameterization, making the choice of a fitting algorithm difficult. We propose a graph layout evaluation system where a user - a researcher or visualization designer - can upload own graphs, select preloaded ones, or generate synthetic graphs to explore different layouts through their generated layouts. The system allows for configuration of multiple layouts that can then be explored by the user using side-by-side comparison and an enlarged view. Further, the system allows for computation of layout metrics. The overview of different layouts and associated layout metrics can then be used to select a fitting algorithm. The system is prepared for further layout algorithms and layout quality metrics, building a starting point for graph layout research.EuroVis 2025 - PostersPosters and Demo
Ambiances Integration in the HBIM Process Towards an Ambient Twin: A Literature Review
No full textThis paper discusses new methods for digitally valorizing a heritage by proposing the inclusion of sensory and atmospheric dimensions within Heritage Building Information Modeling (HBIM) workflows. The age of digital transformation has afforded unprecedented tools through immersive technologies and Information and Communication Technologies (ICT), with which to enrich heritage beyond its geometric documentation. Instead of reframing or transforming the experiences of cultural heritage, we propose to turn to a poetic-sensory model with an awareness of the ambient as the mediation between the physical and experiential dimensions. Through a critical literature review and analysis of HBIM projects in Tunis (Tunisia) and Nantes (France), we both take stock of current practices and suggest future possibilities for defining ambient and in-tangible knowledge using HBIM as the modality. Importantly, our Research supports the evolution of digital twins to encompass ambient twins, to document, capture and ultimately portray emotional attachments and cultural significance of heritage places. The proposed model is currently being developed within the framework of a joint PhD. The case studies in Tunis and Nantes aim to identify relevant tools and methods to capture, store, and integrate atmospheric data into HBIM environments.Digital HeritagePoster
DashGuide: Authoring Interactive Dashboard Tours for Guiding Dashboard Users
No full textDashboard guidance helps dashboard users better navigate interactive features, understand the underlying data, and assess insights they can potentially extract from dashboards. However, authoring dashboard guidance is a time consuming task, and embedding guidance into dashboards for effective delivery is difficult to realize. In this work, we contribute DASHGUIDE, a framework and system to support the creation of interactive dashboard guidance with minimal authoring input. Given a dashboard and a communication goal, DASHGUIDE captures a sequence of author-performed interactions to generate guidance materials delivered as playable step-by-step overlays, a.k.a., dashboard tours. Authors can further edit and refine individual tour steps while receiving generative assistance. We also contribute findings from a formative assessment with 9 dashboard creators, which helped inform the design of DASHGUIDE; and findings from an evaluation of DASHGUIDE with 12 dashboard creators, suggesting it provides an improved authoring experience that balances efficiency, expressiveness, and creative freedom.Computer Graphics ForumStorytelling, Integration of Visualization and Tex
DeepFracture: A Generative Approach for Predicting Brittle Fractures with Neural Discrete Representation Learning
No full textIn the field of brittle fracture animation, generating realistic destruction animations using physics‐based simulation methods is computationally expensive. While techniques based on Voronoi diagrams or pre‐fractured patterns are effective for real‐time applications, they fail to incorporate collision conditions when determining fractured shapes during runtime. This paper introduces a novel learning‐based approach for predicting fractured shapes based on collision dynamics at runtime. Our approach seamlessly integrates realistic brittle fracture animations with rigid body simulations, utilising boundary element method (BEM) brittle fracture simulations to generate training data. To integrate collision scenarios and fractured shapes into a deep learning framework, we introduce generative geometric segmentation, distinct from both instance and semantic segmentation, to represent 3D fragment shapes. We propose an eight‐dimensional latent code to address the challenge of optimising multiple discrete fracture pattern targets that share similar continuous collision latent codes. This code will follow a discrete normal distribution corresponding to a specific fracture pattern within our latent impulse representation design. This adaptation enables the prediction of fractured shapes using neural discrete representation learning. Our experimental results show that our approach generates considerably more detailed brittle fractures than existing techniques, while the computational time is typically reduced compared to traditional simulation methods at comparable resolutions.Computer Graphics ForumOriginal Article44
Efficient and Accurate Optimization in Inverse Rendering and Computer Graphics
No full textEfficient and accurate representation of graphic assets, a long-standing task in the graphics community, has achieved new heights with the advent of learning-based methods by representing visual appearance as neural networks. Surprisingly, such visual appearance networks are often trained from scratch – an expensive operation that ignores potentially helpful information from previous training runs. This thesis therefore introduces Metappearance, an algorithm which optimizes over optimization itself and enables orders of magnitude faster training times at indistinguishable visual quality while retaining the network’s adaptability to new, unseen data. Moreover, even a fully converged network, albeit a smooth function, does not guarantee optimization success when employed in an inverse rendering scenario. In fact, it is common for inverse rendering to exhibit plateaus – regions of zero gradient – in the cost function, which hinder gradient-based optimization from converging. Chapter 4 therefore introduces an algorithm that smooths out such plateaus by convolving the rendering equation with a Gaussian blur kernel and thus successfully optimizes scenarios where other, rigid methods fail to converge. Finally, while recent research has shown that specialized treatment of the renderer’s internals can yield correct, usable gradients, there is no unified, systematic way of differentiating through arbitrary, black-box graphics pipelines. We therefore introduce the concept of neural surrogates, which allow differentiating through arbitrary forward models without requiring access to, or making any assumptions on, the rendering pipeline’s internals. We show that our neural surrogate losses can successfully optimize various graphics tasks and scale well to high dimensions, a domain where traditional derivative-free optimizers often do not converge.The PhD program during which this thesis was developed was sponsored by Meta Reality Labs.EG Graphics Dissertation Onlin
Proximity-Based Point Cloud Reconstruction
No full textExtrapolating information from incomplete data is a key human skill, enabling us to infer patterns and make predictions from limited observations. A prime example is our ability to perceive coherent shapes from seemingly random point sets, a key aspect of cognition. However, data reconstruction becomes challenging when no predefined rules exist, as it is unclear how to connect the data or infer patterns. In computer graphics, a major goal is to replicate this human ability by developing algorithms that can accurately reconstruct original structures or extract meaningful information from raw, disconnected data. The contributions of this thesis deal with point cloud reconstruction, leveraging proximity-based methods, with a particular focus on a specific proximity-encoding data structure - the spheres-of-influence graph (SIG). We discuss curve reconstruction, where we automate the game of connecting the dots to create contours, providing theoretical guarantees for our method. We obtain the best results compared to similar methods for manifold curves. We extend our curve reconstruction to manifolds, overcoming the challenges of moving to different domains, and extending our theoretical guarantees. We are able to reconstruct curves from sparser inputs compared to the state-of-the-art, and we explore various settings in which these curves can live. We investigate the properties of the SIG as a parameter-free proximity encoding structure of three-dimensional point clouds. We introduce new spatial bounds for the SIG neighbors as a theoretical contribution. We analyze how close the encoding is to the ground truth surface compared to the commonly used kNN graphs, and we evaluate our performance in the context of normal estimation as an application. Lastly, we introduce SING – a stability-incorporated neighborhood graph, a useful tool with various applications, such as clustering, and with a strong theoretical background in topological data analysis.EG Graphics Dissertation Onlin
Neighbour Embeddings: Beyond Visualisation
No full textMachine learning (ML) has brought powerful tools to the visualisation community, particularly through neighbour embeddings (NE). This family of algorithms enables the intuitive visualisation of high dimensional datasets, by representing these in 2- or 3-dimensional spaces. This paper argues that as NE algorithms have progressed and diversified within the visualisation domain, they have matured into powerful yet often simple methods whose potential remains largely underutilised in broader machine learning contexts. This argument is illustrated by showing through two use cases, clustering and data preprocessing before a supervised task, how NE can contribute meaningfully with little additional algorithmic effort.Machine Learning Methods in Visualisation for Big DataPaper