Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
Real-time Neural Rendering of LiDAR Point Clouds
No full textStatic LiDAR scanners produce accurate, dense, colored point clouds, but often contain obtrusive artifacts which makes them ill-suited for direct display. We propose an efficient method to render more perceptually realistic images of such scans without any expensive preprocessing or training of a scene-specific model. A naive projection of the point cloud to the output view using 1×1 pixels is fast and retains the available detail, but also results in unintelligible renderings as background points leak between the foreground pixels. The key insight is that these projections can be transformed into a more realistic result using a deep convolutional model in the form of a U-Net, and a depth-based heuristic that prefilters the data. The U-Net also handles LiDAR-specific problems such as missing parts due to occlusion, color inconsistencies and varying point densities. We also describe a method to generate synthetic training data to deal with imperfectly-aligned ground truth images. Our method achieves real-time rendering rates using an off-the-shelf GPU and outperforms the state-of-the-art in both speed and quality.Eurographics 2025 - Short PapersShort Paper
Many-Light Rendering Using ReSTIR-Sampled Shadow Maps
No full textWe present a practical method targeting dynamic shadow maps for many light sources in real-time rendering. We compute fullresolution shadow maps for a subset of lights, which we select with spatiotemporal reservoir resampling (ReSTIR). Our selection strategy automatically regenerates shadow maps for lights with the strongest contributions to pixels in the current camera view. The remaining lights are handled using imperfect shadow maps, which provide low-resolution shadow approximation. We significantly reduce the computation and storage compared to using all full-resolution shadow maps and substantially improve shadow quality compared to handling all lights with imperfect shadow maps.Computer Graphics ForumLighting the Way: Scattering and Transport in Rendering44
Spatial random access to explore heritage site using spherical video
No full textSpherical images are particularly adapted to develop virtual tours of heritage monuments. While Lidar scanning, photogram- metry and rotating camera systems can lead to produce spherical images, compact dual-fisheye cameras are accurate enough for many uses, such as virtual tour, and easy to use by a non-expert. But the classical software consider placing a few im- ages manually on the blueprint of the environment. Then, the user navigation in the virtual monument is limited to generated transitions between a few locations. Instead of a few pictures, this paper considers a spherical video recorded while walking within a monument and illustrates how to explore spatial dimensions of the environment where the video was taken, beyond the time scroll-bar. To this end, spherical visual Simultaneous Localization And Mapping (SLAM) and the alignment of the resulting map to an architectural blueprint are combined to create a spatio-temporal virtual tour from a video. The concept is demonstrated on the al-Qarawiyyin Mosque in Fez, Morocco, with access to the virtual tour interface at this link: https://home.mis.u-picardie.fr/~ecathedrale/alQarawiyyin/.Digital HeritageDigitization Case Studie
Motivating Through Design: Affective Visualization in mHealth
No full textLow retention and limited public health impact remain persistent challenges for mobile health (mHealth) apps [MAD*22]. This study explores affective visualization as a solution, advocating for a post-cognitivist perspective in defining the future of affective design. This approach proposes that technology should not tell users what or how to act or think but instead respond to how human minds work. This framework could transform user communication through visualization, fostering positive behavioural changes. The study also highlights affective visualization as a nascent yet promising domain for future research [LWC23].EuroVis 2025 - PostersPoster
Web3D Publishing Tools and Techniques for Digital Heritage
No full textIn the rapidly evolving landscape of digital heritage, the integration of Web3D technologies offers unprecedented opportunities for the preservation and dissemination of cultural heritage assets. This tutorial aims to equip participants with essential tools and techniques for effective Web3D publishing, focusing on methodologies that enhance accessibility, interactivity, and interoperability with digital heritage content. This tutorial will provide hands-on activities and live demonstrations to attendees, delivered by multiple presenters on the topics of web-friendly 3D formats, importance of metadata and interoperability, content authoring applications, and their associated content development pipelines.Digital HeritageTutorial
Digital technologies for the ''Grazia Deledda'' Literary Park in Galtellì (NU): the 3D virtual reconstruction of Pontes Castle
No full textThis paper aims to present one of the digital outputs of the ongoing project to enhance the Grazia Deledda Literary Park in Galtellì: the virtual reconstruction of the medieval Pontes Castle, located in an impervious and hard-to-reach area. Although it is now difficult to identify the original structure, historical research, graphic reconstructions, surveys, and the restoration and consolidation works provide valuable information about its layout, which can be further expanded and improved thanks to the application of digital technologies. The 3D digitization of Pontes Castle using Gaussian Splatting introduces a new way of documenting cultural heritage through photorealistic reconstruction without polygonal meshes. This technique enables real-time interactive visualization, reducing processing time compared to traditional photogrammetry while offering a more natural handling of light and details. At the same time, to assess the benefits offered by this technique, the field data will also be processed using well-established software in the field of classical photogrammetry. In this regard, the results obtained with conventional techniques can serve as a ground-truth reference to verify the quality of the 3D-GS point cloud.Digital HeritageDigital Technologies for CHANGES (CHANGES SESSION) - Part
SOBB: Skewed Oriented Bounding Boxes for Ray Tracing
No full textWe propose skewed oriented bounding boxes (SOBB) as a novel bounding primitive for accelerating the calculation of rayscene intersections. SOBBs have the same memory footprint as the well-known oriented bounding boxes (OBB) and can be used with a similar ray intersection algorithm. We propose an efficient algorithm for constructing a BVH with SOBBs, using a transformation from a standard BVH built for axis-aligned bounding boxes (AABB). We use discrete orientation polytopes as a temporary bounding representation to find tightly fitting SOBBs. Additionally, we propose a compression scheme for SOBBs that makes their memory requirements comparable to those of AABBs. For secondary rays, the SOBB BVH provides a ray tracing speedup of 1.0-11.0x over the AABB BVH and it is 1.1x faster than the OBB BVH on average. The transformation of AABB BVH to SOBB BVH is, on average, 2.6x faster than the ditetrahedron-based AABB BVH to OBB BVH transformation.Computer Graphics ForumReal-Time Rendering: Fast, Furious, and Accurate44
Non-Invasive Detection and Characterization of Powdery Mildew in Strawberries Using Hyperspectral Imaging and Deep Learning under Poly-tunnel Conditions
No full textPowdery Mildew (Podosphaera aphanis, PM) presents a serious challenge to strawberry cultivation, causing significant yield losses if not controlled early. Globally, PM contributes to substantial reductions in strawberry production, posing economic threats to growers and raising food security concerns. Therefore, the development of accurate, noninvasive detection mechanisms is crucial for effective disease management. This study investigates the application of Hyperspectral Imaging (HSI) for nondestructive PM detection and classification of healthy and PM-infected strawberry leaves grown under a poly-tunnel, an environment that closely simulates real-world agricultural conditions. A hyperspectral camera (350-1000 nm), mounted on a mechanized rail system beneath the poly-tunnel, was used to capture leaf images as it moved linearly above the strawberry canopy. Spectral preprocessing included Savitzky-Golay smoothing (SGS), Standard Normal Variate (SNV), and Multiplicative Scatter Correction (MSC), with the Isolation Forest algorithm applied for outlier removal. A one-dimensional Convolutional Neural Network (1D-CNN) was trained to classify healthy versus PM-infected leaves, achieving 75% accuracy and 84% precision. The model outperformed traditional classifiers such as Random Forest (RF), Decision Tree (DT), and Partial Least Squares Discriminant Analysis (PLS-DA). Among all tested pipelines, the SGS+MSC+1D-CNN combination yielded the highest performance. This study highlights the feasibility and effectiveness of integrating HSI with deep learning for robust disease detection under semi-controlled conditions, laying the groundwork for scalable, real-time plant health monitoring in precision agriculture.Computer Graphics and Visual Computing (CGVC)Computer Vision for Graphic
Reducing Visible Staircasing Artifacts Through Printing Orientation Using a Perception-Driven Metric
No full text3D printing is widely used for prototyping and fabricating custom designs. Due to the discretization introduced during printing, the quality of the fabricated surfaces often suffers from so-called staircasing artifacts. While all 3D printers produce these artifacts, their severity depends on the printing resolution. Thus, these artifacts are particularly pronounced in low- to medium-cost printers, which are commonly used by home users, hobbyists, and enthusiasts of 3D printing. Changing the printing orientation allows for reducing the artifacts, enabling more accurate surface reproduction. While several previous works exploited this idea, they formulated the problem based on the geometrical accuracy of surface reproduction. This paper takes a different approach that focuses on the perception of the surface appearance. Our work is motivated by the fact that the visual severity of the artifacts depends on the characteristics of the patterns that the staircasing produces. These are also influenced by the viewing conditions, i.e., lighting and viewing orientations. Consequently, we develop in this paper a perception-inspired technique for quantifying the visibility of staircasing artifacts that takes the above factors into consideration. It is grounded in the human contrast sensitivity function, which models the ability of the human visual system to detect spatial patterns. Using the method, we propose an optimization procedure for finding the printing orientation for 3D models, which minimizes the visibility of staircasing artifacts. We evaluate our method against geometric approaches across a range of 3D models and viewing conditions. Our user study confirms the effectiveness of our approach in reducing the visual impact of staircasing artifacts.Pacific Graphics Conference Papers, Posters, and DemosFabrication & Artistic design