Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
SPG: Style-Prompting Guidance for Style-Specific Content Creation
No full textAlthough recent text-to-image (T2I) diffusion models excel at aligning generated images with textual prompts, controlling the visual style of the output remains a challenging task. In this work, we propose Style-Prompting Guidance (SPG), a novel sampling strategy for style-specific image generation. SPG constructs a style noise vector and leverages its directional deviation from unconditional noise to guide the diffusion process toward the target style distribution. By integrating SPG with Classifier- Free Guidance (CFG), our method achieves both semantic fidelity and style consistency. SPG is simple, robust, and compatible with controllable frameworks like ControlNet and IPAdapter, making it practical and widely applicable. Extensive experiments demonstrate the effectiveness and generality of our approach compared to state-of-the-art methods. Code is available at https://github.com/Rumbling281441/SPG.Computer Graphics ForumStylization44
Architectural Surveying, from Point Cloud to CAD/BIM: Towards Automation of Data Processing for Large-Scale Projects
No full textAs part of a project to digitize the infrastructure of the Université Libre de Bruxelles, a semi-automated digital acquisition methodology was developed to create a 3D inventory of the buildings on the Solbosch Campus. The objective is to build an up-to-date graphical database to facilitate the daily maintenance of the sites and support future renovation projects. A systematic workflow was therefore established: one that is both tailored to the constraints, challenges, and goals specific to each building, and that incorporates automated data processing methods to ensure efficiency, consistency, and scientific accuracy throughout the acquisition process. The ultimate aim is to produce coherent datasets that are aligned with one another, streamlining procedures for projects of similar nature and scale. The long-term value of this approach lies in the potential to fully automate certain stages of the workflow, thereby improving efficiency while maintaining high standards of data accuracy.Digital HeritagePoster
Evaluating the role of video within multi-sensory cultural experiences
No full textThis short paper reports a recent experiment with digital content and its evaluation in terms of impact in multi-sensory visiting experience, by recording visitors' opinion during its use within a cultural exhibition. Specifically, the aim of this experiment was to understand if and how QR code-enabled video can enhance the multi-sensory visiting experience within a cultural exhibition. This research aims to answer the following three research questions: a) Is QR code-enabled video supportive in the multi-sensory visiting experience of cultural exhibitions? b) How can QR code-enabled video keep the audience's interest in terms of the exhibition's content/subject? c) Can a QR code-enabled video activate visitors' emotions and enrich their sensory experience? To achieve this goal, five videos and a quiz were developed and afterwards evaluated by a traditional hard-copy questionnaire. The findings of this experiment are briefly presented in this paper.Digital HeritageNarratives, Multimodality, and Emotional Engagement in Heritag
Quantised Global Autoencoder: A Holistic Approach to Representing Visual Data
No full textQuantised autoencoders usually split images into local patches, each encoded by one token. This representation is potentially inefficient, as the same number of tokens are spent per region, regardless of the visual information content in that region. To mitigate uneven distribution of information content, modern architectures provide an adaptive discretisation or add an attention mechanism to the autoencoder to infuse global information into the local tokens. Despite these improvements, tokens are still associated with a local image region. In contrast, our method is inspired by spectral decompositions which transform an input signal into a superposition of global frequencies. Taking the data-driven perspective, we train an encoder that produces a combination of tokens that are then decoded jointly, going beyond the simple linear superposition of spectral decompositions. We achieve this global description with an efficient transpose operation between features and channels and demonstrate how our global and holistic representation improves compression and can boost downstream tasks like generation.Vision, Modeling, and VisualizationNeural and Differentiable Renderin
Advancing XR Education: Towards a Multimodal Human-Machine Interaction Course for Doctoral Students in Computer Science
No full textNowadays, eXtended Reality (XR) has matured to the point where it seamlessly integrates various input and output modalities, enhancing the way users interact with digital environments. From traditional controllers and hand tracking to voice commands, eye tracking, and even biometric sensors, XR systems now offer more natural interactions. Similarly, output modalities have expanded beyond visual displays to include haptic feedback, spatial audio, and others, enriching the overall user experience. In this vein, as the field of XR becomes increasingly multimodal, the education process must also evolve to reflect these advancements. There is a growing need to incorporate additional modalities into the curriculum, helping students understand their relevance and practical applications. By exposing students to a diverse range of interaction techniques, they can better assess which modalities are most suitable for different contexts, enabling them to design more effective and human-centered solutions. This work describes an Advanced Human-Machine Interaction (HMI) course aimed at Doctoral Students in Computer Science. The primary objective is to provide students with the necessary knowledge in HMI by enabling them to articulate the fundamental concepts of the field, recognize and analyze the role of human factors, identify modern interaction methods and technologies, apply HCD principles to interactive system design and development, and implement appropriate methods for assessing interaction experiences across advanced HMI topics. In this vein, the course structure, the range of topics covered, assessment strategies, as well as the hardware and infrastructure employed are presented. Additionally, it highlights mini-projects, including flexibility for students to integrate their projects, fostering personalized and project-driven learning. The discussion reflects on the challenges inherent in keeping pace with this rapidly evolving field and emphasizes the importance of adapting to emerging trends. Finally, the paper outlines future directions and potential enhancements for the course.Eurographics 2025 - Education PapersEducation
Using Saliency for Semantic Image Abstractions in Robotic Painting
No full textWe present an adaptive, semantics-based abstraction approach that balances aesthetic quality and structural coherence within the practical constraints of robotic painting. We apply panoptic segmentation with color-based over-segmentation to partition images into meaningful regions aligned with semantic objects, while providing flexible abstraction levels. Automatic parameter selection for region merging is enabled by semantic saliency maps, derived from Out-of-Distribution segmentation techniques in combination with machine learning methods for feature detection. This preserves the boundaries of salient objects while simplifying less prominent regions. A graph-based community detection step further refines the abstraction by grouping regions according to local connectivity and semantic coherence. The runtime of our method outperforms optimization-based image vectorization methods, enabling the efficient generation of multiple abstraction levels that can serve as hierarchical layers for robotic painting. We demonstrate the quality of our method by showing abstraction results, robotic paintings with the e-David robot, and a comparison to other abstraction methods.Computer Graphics ForumStylization44
Player-Centric Shot Maps in Table Tennis
No full textShot maps are popular in many sports as they typically plot events and player positions in the way they are collected, using a pitch or a table as an absolute coordinate system. We introduce a variation of a table tennis shot map that shifts the point of view from the table to the player. This results in a new reference system to plot incoming balls relative to the player's position rather than on the table. This approach aligns with how table tennis tactical analysis is conducted, focusing on identifying empty spaces and weak spots around the players. We describe the motivation behind this work, built through close collaboration with two table tennis experts, and demonstrate how this approach aligns with the way they analyze games to reveal key tactical aspects. We also present the design rationale and the computer vision pipeline used to accurately collect data from broadcast videos. Our findings show that the technique enables capturing insights that were not visible with the absolute coordinate system, particularly in understanding regions that are reachable and those close to the pivot area of the player.Computer Graphics ForumSports, Gaming, and Behavioral Pattern
Fast HARDI Uncertainty Quantification and Visualization with Spherical Sampling
No full textIn this paper, we study uncertainty quantification and visualization of orientation distribution functions (ODF), which corresponds to the diffusion profile of high angular resolution diffusion imaging (HARDI) data. The shape inclusion probability (SIP) function is the state-of-the-art method for capturing the uncertainty of ODF ensembles. The current method of computing the SIP function with a volumetric basis exhibits high computational and memory costs, which can be a bottleneck to integrating uncertainty into HARDI visualization techniques and tools. We propose a novel spherical sampling framework for faster computation of the SIP function with lower memory usage and increased accuracy. In particular, we propose direct extraction of SIP isosurfaces, which represent confidence intervals indicating spatial uncertainty of HARDI glyphs, by performing spherical sampling of ODFs. Our spherical sampling approach requires much less sampling than the state-of-the-art volume sampling method, thus providing significantly enhanced performance, scalability, and the ability to perform implicit ray tracing. Our experiments demonstrate that the SIP isosurfaces extracted with our spherical sampling approach can achieve up to 8164× speedup, 37282× memory reduction, and 50.2% less SIP isosurface error compared to the classical volume sampling approach. We demonstrate the efficacy of our methods through experiments on synthetic and human-brain HARDI datasets.Computer Graphics ForumUncertainty, Sensitivity, Scalabilit
3D Data in the Data Space for Cultural Heritage
No full textThe common European data space for cultural heritage is an initiative of the European Union, funded under its Digital Europe programme. It supports the digital transformation of Europe's cultural sector and allows cultural heritage institutions across Europe to share digitised cultural heritage content, with high-quality metadata, including in 3D, to promote the reuse of digitised cultural heritage among various audiences, creating value for the economy and society. The workshop is dedicated to (1) to provide an insight in the Data Space for Cultural Heritage and the supporting projects carried out particularly to deal with 3D assets. (2) To discuss the impact of those endeavours with regards to overarching challenges as data, standards, capacities and application, (3) provide a hands-one experience with innovative tools.Digital HeritageWorkshop
MPACT: Mesoscopic Profiling and Abstraction of Crowd Trajectories
No full textSimulating believable crowds for applications like movies or games is challenging due to the many components that comprise a realistic outcome. Users typically need to manually tune a large number of simulation parameters until they reach the desired results. We introduce MPACT, a framework that leverages image-based encoding to convert unlabelled crowd data into meaningful and controllable parameters for crowd generation. In essence, we train a parameter prediction network on a diverse set of synthetic data, which includes pairs of images and corresponding crowd profiles. The learned parameter space enables: (a) implicit crowd authoring and control, allowing users to define desired crowd scenarios using real-world trajectory data, and (b) crowd analysis, facilitating the identification of crowd behaviours in the input and the classification of unseen scenarios through operations within the latent space. We quantitatively and qualitatively evaluate our framework, comparing it against real-world data and selected baselines, while also conducting user studies with expert and novice users. Our experiments show that the generated crowds score high in terms of simulation believability, plausibility and crowd behaviour faithfulness.Computer Graphics ForumOriginal Article44