Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
ServeSense: Interactive VR Tennis Serve Training System Enhanced with Haptic Feedback
No full textTennis serves are a crucial aspect of the sport, often dictating the rhythm of a match and providing players with a competitive edge. While previous studies have explored the use of virtual reality (VR) to enhance tennis performance, they have largely overlooked the significance of tennis serves. To address this gap, the proposed ServeSense integrates gaming elements with Arduino hardware to enhance realism through haptic feedback. Users train in a gamified, fantasy environment, engaging in immersive and interactive tennis serve challenges. The system is designed to motivate user engagement while improving training efficiency.Pacific Graphics Conference Papers, Posters, and DemosPosters and Demo
How to Train Your Dragon: Automatic Diffusion-Based Rigging for Characters with Diverse Topologies
No full textRecent diffusion-based methods have achieved impressive results on animating images of human subjects. However, most of that success has built on human-specific body pose representations and extensive training with labeled real videos. In this work, we extend the ability of such models to animate images of characters with more diverse skeletal topologies. Given a small number (3-5) of example frames showing the character in different poses with corresponding skeletal information, our model quickly infers a rig for that character that can generate images corresponding to new skeleton poses. We propose a procedural data generation pipeline that efficiently samples training data with diverse topologies on the fly. We use it, along with a novel skeleton representation, to train our model on articulated shapes spanning a large space of textures and topologies. Then during fine-tuning, our model rapidly adapts to unseen target characters and generalizes well to rendering new poses, both for realistic and more stylized cartoon appearances. To better evaluate performance on this novel and challenging task, we create the first 2D video dataset that contains both humanoid and non-humanoid subjects with per-frame keypoint annotations. With extensive experiments, we demonstrate the superior quality of our results.Computer Graphics ForumRigged for Success: Character Animation and Retargeting44
NCD: Normal-Guided Chamfer Distance Loss for Watertight Mesh Reconstruction from Unoriented Point Clouds
No full textAs a widely used loss function in learnable watertight mesh reconstruction from unoriented point clouds, Chamfer Distance (CD) efficiently quantifies the alignment between the sampled point cloud from the reconstructed mesh and its corresponding input point cloud. Occasionally, to enhance reconstruction fidelity, CD incorporates a normal consistency term, albeit at the cost of efficiency. In this context, normal estimation for unoriented point clouds requires computationally intensive matrix decomposition or specialized pre-trained models, whereas deriving normals for mesh-sampled points can be readily achieved using the cross product of mesh vertices. However, the reconstruction models employing CD and its variants typically rely solely on the spatial coordinates of the points, which omits normal information in favor of efficiency and deployability. To tackle this challenge, we propose a novel loss function for watertight mesh reconstruction from unoriented point clouds, termed Normal-guided Chamfer Distance (NCD). Building upon CD, NCD introduces a normal-steered weighting mechanism based on the angle between the normal at each mesh-sampled point and the vector to its corresponding input point, offering several advantages: (i) it leverages readily available mesh-sampled point normals to weight coordinate-based Euclidean distances, thus extending the capability of CD; (ii) it eliminates the need for normal estimation from input unoriented point clouds; (iii) it incurs a negligible increase in computational complexity compared to CD. We employ NCD as the training loss for point-to-mesh reconstruction with multiple models and initial watertight meshes on benchmark datasets, demonstrating its superiority over state-of-the-art CD variants.Computer Graphics ForumOriginal Article44
Sequence Tube Maps for Structural Variants
No full textDiscovery of large sequence changes-structural variants-is crucial yet challenging in genomics. Pangenome graphs aid in their detection, representing DNA of multiple species as a unified structure. Sequence Tube Maps (STM) visualize these graphs as metro maps but quickly become cluttered. Based on STM, we present SVSTM, which addresses this challenge by reducing visual elements and enabling adjustable detail levels. Overview+detail views highlight large variants, summarize small ones, and offer details on demand. We show SVSTM's utility through use cases and evaluations with domain experts and developers.EuroVis 2025 - Short PapersTechniques and Tool
GUIDÆTA - A Versatile Interactions Dataset with extensive Context Information and Metadata
No full textInteraction data is widely used in multiple domains such as cognitive science, visualization, human computer interaction, and cybersecurity, among others. Applications range from cognitive analyses over user/behavior modeling, adaptation, recommendations, to (user/bot) identification/verification. That is, research on these applications - in particular those relying on learned models - require copious amounts of structured data for both training and evaluation. Different application domains thereby impose different requirements. I.e., for some purposes it is vital that the data is based on a guided interaction process, meaning that monitored subjects pursued a given task, while other purposes require additional context information, such as widget interactions or metadata. Unfortunately, the amount of publicly available datasets is small and their respective applicability for specific purposes limited. We present GUIDEd Interaction DATA (GUIDÆTA) - a new dataset, collected from a large-scale guided user study with more than 250 users, each working on three pre-defined information retrieval tasks using a custom-built consumer information system. Besides being larger than most comparable datasets - with 716 completed tasks, 2.39 million mouse and keyboard events (2.35 million and 40 thousand, respectively) and a total observation period of almost 50 hours - its interactions exhibit encompassing context information in the form of widget information, triggered (system) events and associated displayed content. Combined with extensive metadata such as sociodemographic user data and answers to explicit feedback questionnaires (regarding perceived usability, experienced cognitive load, pre-knowledge on the information system's topic), GUIDÆTA constitutes a versatile dataset, applicable for various research domains and purposes. Alongside the data itself, we publish the software tools we use for handling and analyzing the dataset.Smart Tools and Applications in Graphics - Eurographics Italian Chapter ConferenceDataset
AI and New Digital Education
No full textThe impact of artificial intelligence (AI) on society and research cannot be underestimated.We urgently needs to address this transformation with a strategic and long-term perspective, also involving historical sciences. From a historical standpoint, artificial intelligence raises three main issues: the use of AI to support research, the reliability of the information generated, and the digital literacy that must be imparted to students. Specifically, it is expected that historical research and student activities will increasingly rely on AI tools, despite current limitations in distinguishing automatically generated content. This challenges us to reverse the problem: how can historians, especially at the academic level, effectively leverage AI and pass these skills on to students? The central challenge lies in learning to speka the language of AI content production, known as prompt engineering. This discipline involves formulating optimized inputs for AI models to obtain more relevant and accurate responses, thereby increasing productivity in historical research without compromising the quality of critical analysis. The goal is not to create a technological tool but to design an innovative approach that enables historians to fully exploit AI's potential while maintaining the centrality of source criticism and methodological rigor. Through advanced application of prompt engineering, historians can improve research, interpretation, and communication processes, addressing some of the traditional challenges associated with historical source analysis. The new methodology aims to equip historians with conceptual tools to manage and analyze large amounts of data, evaluate sources more effectively, and narrate history in a more dynamic and accessible way. Moreover, the integration of AI in teaching will open new opportunities to make learning more interactive and personalized, stimulating students' critical thinking and enhancing their historical understanding. This interdisciplinary approach, combining humanities and computer engineering, will prepare future historians for an increasingly digital research landscape.Digital HeritagePoster
DataWeaver: Authoring Data-Driven Narratives through the Integrated Composition of Visualization and Text
No full textData-driven storytelling has gained prominence in journalism and other data reporting fields. However, the process of creating these stories remains challenging, often requiring the integration of effective visualizations with compelling narratives to form a cohesive, interactive presentation. To help streamline this process, we present an integrated authoring framework and system, DATAWEAVER, that supports both visualization-to-text and text-to-visualization composition. DATAWEAVER enables users to create data narratives anchored to data facts derived from ''call-out'' interactions, i.e., user-initiated highlights of visualization elements that prompt relevant narrative content. In addition to this ''vis-to-text'' composition, DATAWEAVER also supports a ''text-initiated'' approach, generating relevant interactive visualizations from existing narratives. Key findings from an evaluation with 13 participants highlighted the utility and usability of DATAWEAVER and the effectiveness of its integrated authoring framework. The evaluation also revealed opportunities to enhance the framework by refining filtering mechanisms and visualization recommendations and better support authoring creativity by introducing advanced customization options.Computer Graphics ForumStorytelling, Integration of Visualization and Tex
Controlled Image Variability via Diffusion Processes
No full textDiffusion models have shown remarkable abilities in generating realistic images. Unfortunately, diffusion processes do not directly produce diverse samples. Recent work has addressed this problem by applying a joint-particle time-evolving potential force that encourages varied and distinct generations. However, such a method focuses on improving the diversity across any batch of generation rather than producing variations of a specific sample. In this paper, we propose a method for creating subtle variations of a single (generated) image - specifically, we propose Single Sample Refinement, a simple and training-free method to improve the diversity of one specific sample at different levels of variability. This mode is useful for creative content generation, allowing users to explore controlled variations without sacrificing the identity of the main objects.Eurographics 2025 - Short PapersShort Paper
Generalizing Shape-from-Template to Topological Changes
No full textReconstructing the surfaces of deformable objects from correspondences between a 3D template and a 2D image is well studied under Shape-from-Template (SfT) methods; however, existing approaches break down when topological changes accompany the deformation. We propose a principled extension of SfT that enables reconstruction in the presence of such changes. Our approach is initialized with a classical SfT solution and iteratively adapts the template by partitioning its spatial domain so as to minimize an energy functional that jointly encodes physical plausibility and reprojection consistency. We demonstrate that the method robustly captures a wide range of practically relevant topological events including tears and cuts on bounded 2D surfaces, thereby establishing the first general framework for topological-change-aware SfT. Experiments on both synthetic and real data confirm that our approach consistently outperforms baseline methods.Smart Tools and Applications in Graphics - Eurographics Italian Chapter ConferenceGeometry Processin