Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
Multi-scalar Risk Mapping of Climate Change Impacts on Outdoor Tangible Cultural Heritage: the Case Study of Tortona, Italy
No full textThe wide array of risks posed by climate change to outdoor tangible cultural heritage at different scales necessitates a multidisciplinary and transdisciplinary approach, as well as an initial critical review of existing risk assessment methodologies across various fields. Within this framework, the research conducted by the Sapienza PNRR workgroup has developed a multi-scalar mapping methodology to support the risk assessment process concerning to the multivariate effect of climate change and the interaction of different risks on the tangible outdoor heritage, specifically on the case study of Tortona, Italy.Digital HeritageDigital Technologies for CHANGES (CHANGES SESSION) - Part
Robust Construction of Polycube Segmentations via Dual Loops
No full textPolycube segmentations for 3D models effectively support a wide variety of applications such as seamless texture mapping, spline fitting, structured multi-block grid generation, and hexahedral mesh construction. However, the automated construction of valid polycube segmentations suffers from robustness issues: state-of-the-art methods are not guaranteed to find a valid solution. In this paper we present DualCube: an iterative algorithm which is guaranteed to return a valid polycube segmentation for 3D models of any genus. Our algorithm is based on a dual representation of polycubes. Starting from an initial simple polycube of the correct genus, together with the corresponding dual loop structure and polycube segmentation, we iteratively refine the polycube, loop structure, and segmentation, while maintaining the correctness of the solution. DualCube is robust by construction: at any point during the iterative process the current segmentation is valid. Its iterative nature furthermore facilitates a seamless trade-off between quality and complexity of the solution. DualCube can be implemented using comparatively simple algorithmic building blocks; our experimental evaluation establishes that the quality of our polycube segmentations is on par with, or exceeding, the state-of-the-art.Computer Graphics ForumShape Segmentation and Texturing44
ICAT-EGVE 2025 - Frontmatter
No full textICAT-EGVE 2025 - International Conference on Artificial Reality and Telexistence and Eurographics Symposium on Virtual Environment
Demystifying noise: The role of randomness in generative AI
No full textThis tutorial offers a thorough exploration of the role of randomness in generative AI, leveraging foundational knowledge from statistical physics, stochastic differential equations, and computer graphics. By connecting these disciplines, the tutorial aims to provide participants with a deep understanding of how noise impacts generative modeling and introduce state-of-the-art techniques and applications of noise in AI. First, we revisit the mathematical concepts essential for understanding diffusion and the integral role of noise in diffusion-based generative modeling. In the second part of the tutorial, we introduce the various types of noises studied within the computer graphics community and present their impact on rendering, texture synthesis and content creation. In the last part, we will look at how different noise correlations and noise schedulers impact the expressive power of image and video generation models. By the end of the tutorial, participants will gain an in-depth understanding of the mathematical constructs for diffusion models and how noise correlations can play an important role in enhancing the diversity and expressiveness of these models. The audience will also learn to code these noises developed in the graphics literature and their impact on generative modeling. The tutorial is aimed for students, researchers and practitioners, with our panel members bringing insights from the industry. All the materials related to the tutorial will be available on diffusion-noise.mpi-inf.mpg.de.Eurographics 2025 - TutorialsTutorial
Bringing Emotions into the Picture: the CambiaColore Technology for Socio-emotional Learning in Children
No full textRecognizing our and other people's emotions and being able to express them are key abilities that need to be nurtured and cherished. Technologies can provide teachers and educators with tools that help them engage children in didactic activities, which can foster the development of their emotional abilities. These technologies can also help children find outlets for their emotions, for instance through drawing or expressing emotions with their bodies. This work presents CambiaColore, a novel technology for emotional expression in children. The technology is grounded in the link between drawing and emotion, which is particularly powerful in children and aims to provide teachers with a novel engaging tool for educational, socio-emotional learning activities. Moreover, the technology aims to help children better grasp the interplay between individual and group emotions. The system was co-designed with teachers and educators, who provided incredibly valuable insight regarding its usability and target users. Here, we describe the theoretical premises of our system and its set-up and game-play and present future work directions.ACM/EG Expressive Symposium - WICED: Eurographics Workshop on Intelligent Cinematography and Editing - Artworks, Posters, DemosDem
Advancing Armenian Inscription Recognition
No full textArmenian monuments are rich in carved stone inscriptions. These inscriptions serve as vital records of cultural and linguistic heritage, offering insights into the lives, beliefs, and traditions of Armenians during the Middle ages. However, detecting and comprehending these inscriptions pose significant challenges. Due to weathering, vandalism, erosion, and the complexity of ancient scripts, many of these texts remain unreadable. Yet, the few existing studies indicate that deciphering these messages from the past is feasible with technological advancements. In the present project we study a unique, newly created and unex- plored collection of digital twins of Armenian tapanakars (tombstones) and khachkars (cross-stones) focusing on hierarchical segmentation of the images using the detected geometrical and statistical features. The results are applied to character classi- fication and the accuracy of the generated images is estimated. Since the detection stage of the algorithm is universal for any kind of shapes, it opens up new research avenues that extend beyond text recognition alone. The same pipeline can be adapted to identify decorative motifs, geometric symbols, and other visual patterns commonly found on tapanakar surfaces.Digital HeritageExtracting Knowledge from Digitized Asset
BattleGraphs: Forge, Fortify, and Fight in the Network Arena
No full textConstructive visualization enables users to create personalized data representations and facilitates early insight generation and sensemaking. Based on NODKANT, a toolkit for creating physical network diagrams using 3D printed parts, we define a competitive network physicalization game: BattleGraphs. In BattleGraphs, two players construct networks independently and compete in solving network analysis benchmark tasks. We propose a workshop scenario where we deploy our game, collect strategies for interaction and analysis from our players, and measure the effectiveness of the strategy with the success of the player to discuss in a reflection phase. Printable parts of the game, as well as instructions, are available through the Open Science Framework at https://osf.io/x6zv7/.EuroVis Workshop on Visualization Play, Games, and ActivitiesPaper
Application of LiDAR Sensors for the Reconstruction of the Production Techniques of Artificial Conglomerate Blocks: the Case of the Maconi Tower - Siena (Italy)
No full textThe Maconi tower, dating back to around the 12th century and belonging to one of the leading families of medieval Siena, is characterised, in its internal and external façades, by a wall made of limestone blocks, reused bricks and large blocks of artificial conglomerate. The latter, the subject of this research and also visible in other buildings in the city, are parallelepiped in shape and are made of mortar and angular stone elements, with a texture that varies depending on the size and shape of the aggregates, as well as the processing of the blocks themselves. The aim of the research was to verify the effectiveness of new three-dimensional survey methodologies for the documentation and morphological analysis of artificial conglomerate blocks, in order to understand the production system of the latter. To this end, the LiDAR (Light Detection and Ranging) technology integrated into Apple IPhone PRO devices was used, with which it was possible to obtain detailed 3D scans with the help of a free application and an electronic stabilizer, all accompanied by measurements with traditional systems (comb profiler), used to verify the method. The study concerned, in particular, the evaluation of the roughness of the external surface of the blocks, or the three-dimensional shape of the external faces, as a possible indicator for understanding the methods of construction and processing. The analysis of the surface texture, obtained through three-dimensional scanning, highlighted two types of surfaces in relation to the variation values between the level of the mortar and the top of the stone elements: the first type shows a significant variation, while the second has a more contained difference, indicating a different degree of irregularity. The investigations conducted allowed us to quantify the roughness of the artificial conglomerate blocks, highlighting variations compatible with different exposure to atmospheric agents and/or different construction methods.Digital HeritageCollaborative Cloud for CH (ECHOES SESSION
Global-Local Complementary Representation Network for Vehicle Re-Identification
No full textVehicle Re-Identification (ReID) aims to retrieve images of the same vehicle across multiple non-overlapping cameras. Despite recent advances driven by deep learning, this problem continues to pose challenging due to inter-class similarity and intraclass variation. To address these challenges, we propose a Global-Local Complementary Representation Network (GLCR-Net), which combines global and local features to enhance vehicle ReID accuracy. The global branch employs group convolutions to mitigate overfitting, reduce parameters, and extract comprehensive global features. Meanwhile, the local branch uses a keypoint prediction model to generate keypoint feature maps that are integrated with global features, emphasizing critical regions. Additionally, a Class Activation Mapping (CAM)-based complementary feature learning module is employed to captures features from non-keypoint regions, enriching the feature representation. Experimental results on the VeRi-776 and VehicleID datasets demonstrate that GLCR-Net surpasses state-of-the-art methods in accuracy and generalization. Ablation studies further confirm the effectiveness of group convolutions, keypoint feature integration, and complementary feature learning.Pacific Graphics Conference Papers, Posters, and DemosDetecting & Estimating from image