Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
Geometric Integration for Neural Control Variates
No full textControl variates are a variance-reduction technique for Monte Carlo integration. The principle involves approximating the integrand by a function that can be analytically integrated, and integrating using the Monte Carlo method only the residual difference between the integrand and the approximation, to obtain an unbiased estimate. Neural networks are universal approximators that could potentially be used as a control variate. However, the challenge lies in the analytic integration, which is not possible in general. In this manuscript, we study one of the simplest neural network models, the multilayered perceptron (MLP) with continuous piecewise linear activation functions, and its possible analytic integration. We propose an integration method based on integration domain subdivision, employing techniques from computational geometry to solve this problem in 2D. We demonstrate that an MLP can be used as a control variate in combination with our integration method, showing applications in the light transport simulation.Computer Graphics ForumLighting & Rendering44
NePHIM: A Neural Physics-Based Head-Hand Interaction Model
No full textDue to the increasing use of virtual avatars, the animation of head-hand interactions has recently gained attention. To this end, we present a novel volumetric and physics-based interaction simulation. In contrast to previous work, our simulation incorporates temporal effects such as collision paths, respects anatomical constraints, and can detect and simulate skin pulling. As a result, we can achieve more natural-looking interaction animations and take a step towards greater realism. However, like most complex and computationally expensive simulations, ours is not real-time capable even on high-end machines. Therefore, we train small and efficient neural networks as accurate approximations that achieve about 200 FPS on consumer GPUs, about 50 FPS on CPUs, and are learned in less than four hours for one person. In general, our focus is not to generalize the approximation networks to low-resolution head models but to adapt them to more detailed personalized avatars. Nevertheless, we show that these networks can learn to approximate our head-hand interaction model for multiple identities while maintaining computational efficiency. Since the quality of the simulations can only be judged subjectively, we conducted a comprehensive user study which confirms the improved realism of our approach. In addition, we provide extensive visual results and inspect the neural approximations quantitatively. All data used in this work has been recorded with a multi-view camera rig. Code and data are available at https://gitlab.cs.hs-rm.de/cvmr_releases/HeadHand.Computer Graphics ForumFace-First for Digital Avatars44
Herds From Video: Learning a Microscopic Herd Model From Macroscopic Motion Data
No full textWe present a method for animating herds that automatically tunes a microscopic herd model based on a short video clip of real animals. Our method handles videos with dense herds, where individual animal motion cannot be separated out. Our contribution is a novel framework for extracting macroscopic herd behaviour from such video clips, and then deriving the microscopic agent parameters that best match this behaviour. To support this learning process, we extend standard agent models to provide a separation between leaders and followers, better match the occlusion and field-of-view limitations of real animals, support differentiable parameter optimization and improve authoring control. We validate the method by showing that once optimized, the social force and perception parameters of the resulting herd model are accurate enough to predict subsequent frames in the video, even for macroscopic properties not directly incorporated in the optimization process. Furthermore, the extracted herding characteristics can be applied to any terrain with a palette and region-painting approach that generalizes to different herd sizes and leader trajectories. This enables the authoring of herd animations in new environments while preserving learned behaviour.Computer Graphics ForumMajor Revision from Eurographics Conference44
Creative Processes of the Visual Arts and Generative AI. Correspondences between Michelangelo and Sebastiano Del Piombo in the Flagellation of Christ Ideation
No full textIs it possible to visualize the creative process of the art in the making? How can we display an intangible phenomenon such as artistic research to make it perceivable and knowable? In the Enacting Artistic Research (EAR) project, a series of examples were identified for the choice of a case study that could lend itself to the continuous representation of the creative process. The choice fell on Michelangelo's preparatory drawings for the Flagellation of Christ for the Borgherini Chapel in San Pietro in Montorio, which Sebastiano del Piombo would have completed between 1516 and 1522, followed by other studies and other drawings for the Altarpiece of the Flagellation for the Church of Santa Maria del Paradiso in Viterbo in 1525. This series of drawings is particularly significant because it allows us to follow the changes made from the first idea, or first thought, through the study drawings or cartoons, up to the final phase of the underdrawing which can be read in infrared reflectography under the painting and then in relation to the chosen pictorial solution. It emerges, from this sequence, that Sebastiano lengthens the figure of Christ and rotates his face to accentuate pathos, involving the observer more closely. In order to enhance the creative process, the paper will present a workflow for the analysis, knowledge creation and storytelling of the artistic process, based on Gigapixel images, Artificial Intelligence generative tools and Large Language Models. The idea is to validate previous analysis thanks to the digital approach and to assess new forms of narratives, effectively exploiting the high-quality facsimile as well as the various AI technologies.The pilot case introduces innovative investigative and visual restitution techniques, such as virtual reality (VR), extended reality (XR), advanced imaging, and 3D modeling. Through the collaboration of scientists, 3D experts, and art historians, this groundbreaking approach unveils artistic research within creative processes, opening new avenues of aesthetic understanding.Digital HeritageAnalysing and Documenting the Creation Process, Evolution and Contex
Enhancing Environmental Data Communication Through VR
No full textThis paper examines how environmental data can be effectively communicated to non-experts in interactive, immersive 3D spaces. Utilizing a use case centered on global spatio-temporal CO2 emissions and population dynamics over the past six decades, we explore techniques for presenting both absolute (country-level) and per capita data within meaningful spatial and temporal contexts. We developed a VR prototype visualizing these data on an interactive 3D globe and conducted a qualitative user study to evaluate its clarity and interpretability for non-expert audiences. Our findings suggest that incorporating clear geographical context, intuitive representations, and user-centered interactions can enhance engagement and certain aspects of understanding. We thereby offer a practical contribution to tackling environmental data visualization and communication in immersive environments. This promotes transparency and mitigates the risk of misinterpretation or misinformation in data communication across emerging digital media platforms.Computer Graphics and Visual Computing (CGVC)Short Papers Session: Visualisatio
StyleMM: Stylized 3D Morphable Face Model via Text Driven Aligned Image Translation
No full textWe introduce StyleMM, a novel framework that can construct a stylized 3D Morphable Model (3DMM) based on user-defined text descriptions specifying a target style. Building upon a pre-trained mesh deformation network and a texture generator for original 3DMM-based realistic human faces, our approach fine-tunes these models using stylized facial images generated via text-guided image-to-image (i2i) translation with a diffusion model, which serve as stylization targets for the rendered mesh. To prevent undesired changes in identity, facial alignment, or expressions during i2i translation, we introduce a stylization method that explicitly preserves the facial attributes of the source image. By maintaining these critical attributes during image stylization, the proposed approach ensures consistent 3D style transfer across the 3DMM parameter space through imagebased training. Once trained, StyleMM enables feed-forward generation of stylized face meshes with explicit control over shape, expression, and texture parameters, producing meshes with consistent vertex connectivity and animatability. Quantitative and qualitative evaluations demonstrate that our approach outperforms state-of-the-art methods in terms of identity-level facial diversity and stylization capability. The code and videos are available at kwanyun.github.io/stylemm_page.Computer Graphics ForumStylization44
Real-Time Importance Deep Shadows Maps with Hardware Ray Tracing
No full textRendering shadows for semi-transparent objects like smoke significantly enhances the realism of the final image. With advancements in ray tracing hardware, tracing visibility rays in real time has become possible. However, generating shadows for semi-transparent objects requires evaluating multiple or all intersections along the ray, resulting in a deep shadow ray. Deep Shadow Maps (DSM) offer an alternative but are constrained by their fixed resolution. We introduce Importance Deep Shadow Maps (IDSM), a real-time algorithm that adaptively distributes Deep Shadow samples based on importance captured from the current camera viewport. Additionally, we propose a novel DSM data structure built on the ray tracing acceleration structure, improving performance for scenarios requiring many samples per DSM texel. Our IDSM approach achieves speedups of up to ×6.89 compared to hardware ray tracing while maintaining a nearly indistinguishable quality level.Computer Graphics ForumLight and Brightness44
MetapathVis: Inspecting the Effect of Metapath in Heterogeneous Network Embedding via Visual Analytics
No full textIn heterogeneous graphs (HGs), which offer richer network and semantic insights compared to homogeneous graphs, the technique serves as an essential tool for data mining. This technique facilitates the specification of sequences of entity connections, elucidating the semantic composite relationships between various node types for a range of downstream tasks. Nevertheless, selecting the most appropriate metapath from a pool of candidates and assessing its impact presents significant challenges. To address this issue, our study introduces , an interactive visual analytics system designed to assist machine learning (ML) practitioners in comprehensively understanding and comparing the effects of metapaths from multiple fine‐grained perspectives. allows for an in‐depth evaluation of various models generated with different metapaths, aligning HG network information at the individual level with model metrics. It also facilitates the tracking of aggregation processes associated with different metapaths. The effectiveness of our approach is validated through three case studies and a user study, with feedback from domain experts confirming that our system significantly aids ML practitioners in evaluating and comprehending the viability of different metapath designs.Computer Graphics ForumOriginal Article44
Motion Vector-Based Frame Generation for Real-Time Rendering
No full textThe demand for high frame rate rendering is rapidly increasing, especially in the graphics and gaming industries. Although recent learning-based frame interpolation methods have demonstrated promising results, they have not yet achieved the quality required for real-time gaming. High-quality frame interpolation is critical for rendering faster, dynamic motion during gameplay. In graphics, motion vectors are typically favored over optical flow due to their accuracy and efficiency in game engines. However, motion vectors alone are insufficient for frame interpolation, as they lack bilateral motions for the target frame to interpolate and struggle with capturing non-geometric movements. To address this, we propose a novel method that leverages fast, low-cost motion vectors as guiding flows, integrating them into a task-specific intermediate flow estimation process. Our approach employs a combined motion and image context encoder-decoder to produce more accurate intermediate bilateral flows. As a result, our method significantly improves interpolation quality and achieves state-of-the-art performance in rendered content.Pacific Graphics Conference Papers, Posters, and DemosRendering & Inverse Renderin
Eurographics Workshop on 3D Object Retrieval - Short Papers: Frontmatter
No full textEurographics Workshop on 3D Object Retrieva