Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
VIZTA: Enhancing Comprehension of Distributional Visualization with Visual-Lexical Fused Conversational Interface
No full textComprehending visualizations requires readers to interpret visual encoding and the underlying meanings actively. This poses challenges for visualization novices, particularly when interpreting distributional visualizations that depict statistical uncertainty. Advancements in LLM-based conversational interfaces show promise in promoting visualization comprehension. However, they fail to provide contextual explanations at fine-grained granularity, and chart readers are still required to mentally bridge visual information and textual explanations during conversations. Our formative study highlights the expectations for both lexical and visual feedback, as well as the importance of explicitly linking these two modalities throughout the conversation. The findings motivate the design of VIZTA, a visualization teaching assistant that leverages the fusion of visual and lexical feedback to help readers better comprehend visualization. VIZTA features a semantic-aware conversational agent capable of explaining contextual information within visualizations and employs a visual-lexical fusion design to facilitate chart-centered conversation. A between-subject study with 24 participants demonstrates the effectiveness of VIZTA in supporting the understanding and reasoning tasks of distributional visualization across multiple scenarios.Computer Graphics ForumStorytelling, Integration of Visualization and Tex
Multiview Geometric Regularization of Gaussian Splatting for Accurate Radiance Fields
No full textRecent methods, such as 2D Gaussian Splatting and Gaussian Opacity Fields, have aimed to address the geometric inaccuracies of 3D Gaussian Splatting while retaining its superior rendering quality. However, these approaches still struggle to reconstruct smooth and reliable geometry, particularly in scenes with significant color variation across viewpoints, due to their per-point appearance modeling and single-view optimization constraints. In this paper, we propose an effective multiview geometric regularization strategy that integrates multiview stereo (MVS) depth, RGB, and normal constraints into Gaussian Splatting initialization and optimization. Our key insight is the complementary relationship between MVS-derived depth points and Gaussian Splatting-optimized positions: MVS robustly estimates geometry in regions of high color variation through local patch-based matching and epipolar constraints, whereas Gaussian Splatting provides more reliable and less noisy depth estimates near object boundaries and regions with lower color variation. To leverage this insight, we introduce a median depthbased multiview relative depth loss with uncertainty estimation, effectively integrating MVS depth information into Gaussian Splatting optimization. We also propose an MVS-guided Gaussian Splatting initialization to avoid Gaussians falling into suboptimal positions. Extensive experiments validate that our approach successfully combines these strengths, enhancing both geometric accuracy and rendering quality across diverse indoor and outdoor scenes.Computer Graphics ForumGaussians44
Easy Modeling of Man-Made Shapes in Virtual Reality
No full textVirtual Reality (VR) offers a promising platform for modeling man-made shapes by enabling immersive, hands-on interaction with these 3D shapes. Existing VR tools require either a complex user interface or a post-processing to model fabricable man-made shapes. In this paper, we present a VR tool that enables general users to interactively model man-made shapes for personalized fabrication, simply by using four common hand gestures as the interaction input. This is achieved by proposing an approach that models complex man-made shapes using a small set of geometric operations, and then designing a user interface that intuitively maps four common hand gestures to these operations. In our shape modeling approach, each shape part is modeled as a generalized cylinder with a specific shape type and iteratively assembled in a structure-aware manner to form a fabricable and usable man-made shape. In our user interface, each hand gesture is associated with a specific kind of interaction tasks and is intelligently utilized for performing the small set of operations to create, edit, and assemble generalized cylinders. A user study was conducted to demonstrate that our VR tool allows general users to effectively and creatively model a variety of man-made shapes, some of which have been 3D printed to validate their fabricability and usability.Pacific Graphics Conference Papers, Posters, and DemosInteraction & Virtual Realit
Comparing OCR Pipelines for Folkloristic Text Digitization
No full textThe digitization of historical folkloristic materials presents unique challenges due to diverse text layouts, varying print and handwriting styles, and linguistic variations. This study explores different optical character recognition (OCR) approaches for Slovene folkloristic and historical text digitization, integrating both traditional methods and large language models (LLMs) to improve text transcription accuracy while maintaining linguistic and structural integrity. We compare single-stage OCR techniques with multi-stage pipelines that incorporate machine learning-driven post-processing for text normalization and layout reconstruction. While LLM-enhanced methods show promise in refining recognition outputs and improving readability, they also introduce challenges related to unintended modifications, particularly in the preservation of dialectal expressions and historical structures. Our findings provide insights into selecting optimal digitization strategies for large-scale folklore archives and outline recommendations for developing robust OCR pipelines that balance automation with the need for textual authenticity in digital humanities research.Digital HeritageDigitization and Segmentatio
Animating Vehicles Risk-Aware Interaction with Pedestrians Using Deep Reinforcement Learning
No full textThis paper introduces a deep reinforcement learning-based system for ego vehicle control, enabling interaction with dynamic objects like pedestrians and animals. These objects display varied crossing behaviors, including sudden stops and directional shifts. The system uses a perception module to identify road structures, key pedestrians, inner wheel difference zones, and object movements. This allows the vehicle to make context-aware decisions, such as yielding, turning, or maintaining speed. The training process includes reward terms for speed, time, time-to-collision, and cornering to refine policy learning. Experiments show ego vehicles can adjust their behavior, such as decelerating or yielding, to avoid collisions. Ablation studies highlighted the importance of specific reward terms and state components. Animation results show that ego vehicles could safely interact with pedestrians or animals that exhibited sudden acceleration, mid-crossing directional changes, and abrupt stops.Pacific Graphics Conference Papers, Posters, and DemosVehicle Dynamics and Interaction
FRAMES: A Platform for Constructing Immersive and Multimodal Extended Reality Exhibitions
No full textWhile immersive technologies are becoming more prevalent in museums and exhibition spaces, significant opportunities remain to enhance visitor engagement through more interactive and meaningful experiences. At the same time, physical space limitations often restrict the number of artifacts on display, preventing institutions from showcasing the full richness of their collections to the public. To address these challenges, a platform named FRAMES was designed and developed. Initially implemented in a CAVE-like environment, FRAMES facilitates multi-user interactivity and social engagement, promotes cultural heritage dissemination, and supports the digital transformation of museum experiences. Key features include personalized interactions, accessibility, and Augmented Reality enhancements. To demonstrate its capabilities, VanoArt, an instance of FRAMES for art galleries, was created. A cognitive evaluation with UX experts confirmed the system's effectiveness in enhancing immersion, interactivity, and user engagement. These findings highlight FRAMES' potential to reshape digital exhibition practices and enrich cultural experiences.Digital HeritageXR Platforms and Frameworks for Cultural Engagemen
Evaluating Autoencoders for Parametric and Invertible Multidimensional Projections
No full textRecently, neural networks have gained attention for creating parametric and invertible multidimensional data projections. Parametric projections allow for embedding previously unseen data without recomputing the projection as a whole, while invertible projections enable the generation of new data points. However, these properties have never been explored simultaneously for arbitrary projection methods. We evaluate three autoencoder (AE) architectures for creating parametric and invertible projections. Based on a given projection, we train AEs to learn a mapping into 2D space and an inverse mapping into the original space. We perform a quantitative and qualitative comparison on four datasets of varying dimensionality and pattern complexity using t-SNE. Our results indicate that AEs with a customized loss function can create smoother parametric and inverse projections than feed-forward neural networks while giving users control over the strength of the smoothing effect.EuroVis Workshop on Visual Analytics (EuroVA)Visual Analytics Methods and Approache
Hardware Accelerated Neural Block Texture Compression with Cooperative Vectors
No full textIn this work, we present an extension to the neural texture compression method of Weinreich and colleagues [WDOHN24]. Like them, we leverage existing block compression methods which permit to use hardware texture filtering to store a neural representation of physically-based rendering (PBR) texture sets (including albedo, normal maps, roughness, etc.). However, we show that low dynamic range block compression formats still make the solution viable. Thanks to this, we show that we can achieve higher compression ratio or higher quality at fixed compression ratio. We improve performance at runtime using a tile based rendering architecture that leverage hardware matrix multiplication engine. Thanks to all this, we render 4k textures sets (9 channels per asset) with anisotropic filtering at 1080p using only 28MB of VRAM per texture set at 0.55ms on an Intel B580.High-Performance Graphics - Symposium PapersNeural Textures and Encoding
Representing Animatable Avatar via Factorized Neural Fields
No full textFor reconstructing high-fidelity human 3D models from monocular videos, it is crucial to maintain consistent large-scale body shapes along with finely matched subtle wrinkles. This paper explores how per-frame rendering results can be factorized into a pose-independent component and a corresponding pose-dependent counterpart to facilitate frame consistency at multiple scales. Pose adaptive texture features are further improved by restricting the frequency bands of these two components. Pose-independent outputs are expected to be low-frequency, while high-frequency information is linked to pose-dependent factors. We implement this with a dual-branch network. The first branch takes coordinates in the canonical space as input, while the second one additionally considers features outputted by the first branch and pose information of each frame. A final network integrates the information predicted by both branches and utilizes volume rendering to generate photo-realistic 3D human images. Through experiments, we demonstrate that our method consistently surpasses all state-of-the-art methods in preserving high-frequency details and ensuring consistent body contours. Our code is accessible at https://github.com/ChunjinSong/facavatar.Computer Graphics ForumAnimation and Morphing44
A Process-Oriented Approach to Analyze Analysts' Use of Visualizations: Revealing Insights into the What, When, and How
No full textDespite Visual Analytics (VA) tools being essential for supporting data analysis, evaluating their use in real-world analytical processes remains challenging. Traditional evaluation methods often overlook the nuanced and evolving nature of analysis processes and are not always suitable for investigating scenarios in which analysts combine multiple tools and visualization types. In this paper, we propose a flexible analysis approach for studying analysts' use of visualizations within and across VA tools. Our qualitative method allows researchers to extract user behavior and cognitive steps from screen recordings and think-aloud data and generate event sequences that capture analytic processes. This enables the analysis of usage patterns from multiple perspectives and levels of granularity and allows for the evaluation of effectiveness measures, such as efficiency and accuracy. We demonstrate our approach in the domain of process mining, where our findings provide insights into the use of existing visualizations, and we reflect on lessons learned from this application.Computer Graphics ForumEvaluation and Guidanc