Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
Hybrid Sparse Transformer and Feature Alignment for Efficient Image Completion
No full textIn this paper, we propose an efficient single-stage hybrid architecture for image completion. Existing transformer-based image completion methods often struggle with accurate content restoration, largely due to their ineffective modeling of corrupted channel information and the attention noise introduced by softmax-based mechanisms, which results in blurry textures and distorted structures. Additionally, these methods frequently fail to maintain texture consistency, either relying on imprecise mask sampling or incurring substantial computational costs from complex similarity calculations. To address these limitations, we present two key contributions: a Hybrid Sparse Self-Attention (HSA) module and a Feature Alignment Module (FAM). The HSA module enhances structural recovery by decoupling spatial and channel attention with sparse activation, while the FAM enforces texture consistency by aligning encoder and decoder features via a mask-free, energy-gated mechanism without additional inference cost. Our method achieves state-of-the-art image completion results with the fastest inference speed among single-stage networks, as measured by PSNR, SSIM, FID, and LPIPS on CelebA-HQ, Places2, and Paris datasets.Computer Graphics ForumImage Creation & Augmentation44
Solar Panels on Historic Roofs? A Digital Tool for Assessing Sensitive Roof Areas
No full textThe approval of solar installations on the roofs of listed buildings is a challenge that requires extensive knowledge of the building's roofing materiality, construction and cultural significance. The Lower Saxony State Office for Heritage Preservation (NLD) is leading an interdisciplinary research project with the Institute for Geodesy and Photogrammetry at the Technische Universtität Braunschweig (IGP) to develop a Lower Saxony-wide heritage roof cadastre which enables an initial assessment of the suitability of roofs. The project focuses on creating tools that analyze and evaluate roofs based on their solar potential, roof material, geometry, and visibility in public space. The results can be made publicly accessible by integration into Lower Saxony's geographic information system. This should assist local preservation authorities and those involved in planning to ensure an appropriate and sustainable development of listed buildings in the future.Digital HeritageAnalysing and Documenting Digitized Asset
Introducing Unbiased Depth into 2D Gaussian Splatting for High-accuracy Surface Reconstruction
No full textRecently, 2D Gaussian Splatting (2DGS) has demonstrated superior geometry reconstruction quality than the popular 3DGS by using 2D surfels to approximate thin surfaces. However, it falls short when dealing with glossy surfaces, resulting in visible holes in these areas. We find that the reflection discontinuity causes the issue. To fit the jump from diffuse to specular reflection at different viewing angles, depth bias is introduced in the optimized Gaussian primitives. To address that, we first replace the depth distortion loss in 2DGS with a novel depth convergence loss, which imposes a strong constraint on depth continuity. Then, we rectify the depth criterion in determining the actual surface, which fully accounts for all the intersecting Gaussians along the ray. Qualitative and quantitative evaluations across various datasets reveal that our method significantly improves reconstruction quality, with more complete and accurate surfaces than 2DGS. Code is available at https://github.com/ XiaoXinyyx/Unbiased_Surfel.Computer Graphics ForumGaussian Splatting44
3DGS.zip: A survey on 3D Gaussian Splatting Compression Methods
No full text3D Gaussian Splatting (3DGS) has emerged as a cutting-edge technique for real-time radiance field rendering, offering state-ofthe- art performance in terms of both quality and speed. 3DGS models a scene as a collection of three-dimensional Gaussians, with additional attributes optimized to conform to the scene's geometric and visual properties. Despite its advantages in rendering speed and image fidelity, 3DGS is limited by its significant storage and memory demands. These high demands make 3DGS impractical for mobile devices or headsets, reducing its applicability in important areas of computer graphics. To address these challenges and advance the practicality of 3DGS, this state-of-the-art report (STAR) provides a comprehensive and detailed examination of two complementary yet fundamentally distinct strategies: compression and compaction. Compression techniques focus on reducing the file size by encoding Gaussian attributes more efficiently. In contrast, compaction methods directly optimize the scene's structure by optimizing the number of Gaussian primitives. Notably, while methods in both categories aim to maintain or improve quality, each while minimizing its respective attributes-file size for compression and the number of Gaussians for compaction-compaction does not necessarily lead to smaller file sizes; it specifically targets improved efficiency during rendering, making it distinct from compression. We introduce the basic mathematical concepts underlying the analyzed methods, as well as key implementation details and design choices. Our report thoroughly discusses similarities and differences among the methods, as well as their respective advantages and disadvantages. We establish a consistent framework for comparing the surveyed methods based on key performance metrics and datasets. Specifically, since these methods have been developed in parallel and over a short period of time, currently, no comprehensive comparison exists. This survey, for the first time, presents a unified framework to evaluate 3DGS compression techniques. To facilitate the continuous monitoring of emerging methodologies, we maintain a dedicated website that will be regularly updated with new techniques and revisions of existing findings. Overall, this STAR provides an intuitive starting point for researchers interested in exploring the rapidly growing field of 3DGS compression. By comprehensively categorizing and evaluating existing compression and compaction strategies, our work advances the understanding and practical application of 3DGS in computationally constrained environments.Computer Graphics ForumState of the Art Reports442sta
Smaller than Pixels: Rendering Millions of Stars in Real-Time
No full textMany applications need to display realistic stars. However, rendering stars with their correct luminance is surprisingly difficult: Usually, stars are so far away from the observer, that they appear smaller than a single pixel. As one can not visualize objects smaller than a pixel, one has to either distribute a star's luminance over an entire pixel or draw some kind of proxy geometry for the star. We also have to consider that pixels at the edge of the screen cover a smaller portion of the observer's field of view than pixels in the centre. Hence, single-pixel stars at the edge of the screen have to be drawn proportionally brighter than those in the centre. This is especially important for virtual-reality or dome renderings, where the field of view is large. In this paper, we compare different rendering techniques for stars and show how to compute their luminance based on the solid angle covered by their geometric proxies. This includes point-based stars, and various types of camera-aligned billboards. In addition, we present a software rasterizer which outperforms these classic rendering techniques in almost all cases. Furthermore, we show how a perception-based glare filter can be used to efficiently distribute a star's luminance to neighbouring pixels. Our implementation is part of the open-source space-visualization software CosmoScout VR.Eurographics 2025 - Short PapersShort Paper
Intangible Heritage and Encoded Memory
No full textThis short paper discusses the development of an ongoing project, Threads, a practice-led visual case study that seeks to excavate, illustrate and question encoded memory within transcultural inherited objects of the twice migrant diaspora. Driven by a need to coax memories from loss and posit an alternative interpretation to Indian diasporic histories (specifically twice migrant, India to East Africa and then to UK) and memories which cannot be expressed in Eurocentric terms, Threads explores and seeks to discover what Paul Gilroy (1988) [Gil88] described as the 'memory stored in safekeeping until a means of translation can be found.' As such, the process of development considers media archaeology, applied creative technologies, inherited media archives, intangible and fragile heritage, and transnational objects (textiles). Arguably the case study sits within the context of Stuart Hall's (1999) [Hal99] observation of the creation of 'the new' and the transgressive alongside the traditional and the 'preservation of the past.'Digital HeritagePoster
Digitisation of the Plaster Casts of Lia and Rachele from the Tomb of Julius II by Michelangelo: Methodological Workflow for Data Collection and Photogrammetric Acquisition Processes
No full textThis article describes the process for the digitisation through photogrammetric acquisition of the plaster casts of Lia and Rachele from Julius II, located inside the Basilica of San Pietro in Vincoli, Italy. Preserved at the Academy of Fine Arts of Florence (ABAFi), these casts have historical and educational significance and are a distinctive feature of a unique institution. The study aims to develop a photogrammetric acquisition that incorporates innovative practices using accessible tools within an academic setting. A protocol has been organized into phases to plan, manage, and standardise the digitisation of ABAFi's sculptural heritage.Digital HeritageDigitization, Documentation, and Dissemination Workflow
Grid Labeling: Crowdsourcing Task-Specific Importance from Visualizations
No full textKnowing where people look in visualizations is key to effective design. Yet, existing research primarily focuses on free-viewingbased saliency models- although visual attention is inherently task-dependent. Collecting task-relevant importance data remains a resource-intensive challenge. To address this, we introduce Grid Labeling - a novel annotation method for collecting task-specific importance data to enhance saliency prediction models. Grid Labeling dynamically segments visualizations into Adaptive Grids, enabling efficient, low-effort annotation while adapting to visualization structure. We conducted a humansubject study comparing Grid Labeling with existing annotation methods, ImportAnnots, and BubbleView across multiple metrics. Results show that Grid Labeling produces the least noisy data and the highest inter-participant agreement with fewer participants while requiring less physical (e.g., clicks/mouse movements) and cognitive effort. An interactive demo and the accompanying dataset are available at https://github.com/jangsus1/Grid-Labeling.EuroVis 2025 - Short PapersTechniques and Tool
