857 results
Search Results
Now showing 1 - 10 of 857
Item Corrigendum to “Making Procedural Water Waves Boundary‐aware”, “Primal/Dual Descent Methods for Dynamics”, and “Detailed Rigid Body Simulation with Extended Position Based Dynamics”(© 2023 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2023) Hauser, Helwig and Alliez, PierreItem Rendering 2023 Symposium Track: Frontmatter(The Eurographics Association, 2023) Ritschel, Tobias; Weidlich, Andrea; Ritschel, Tobias; Weidlich, AndreaItem On the Beat: Analysing and Evaluating Synchronicity in Dance Performances(The Eurographics Association, 2023) Menzel, Malte; Tauscher, Jan-Philipp; Magnor, Marcus; Guthe, Michael; Grosch, ThorstenThis paper presents a method to analyse and evaluate synchronicity in dance performances automatically. Synchronisation of a dancer's movement and the accompanying music is a vital characteristic of dance performances. We propose a method that fuses computer vision-based extraction of dancers' body pose information and audio beat tracking to examine the alignment of the dance motions with the background music. Specifically, the motion of the dancer is analysed for rhythmic dance movements that are then subsequently correlated to the musical beats of the soundtrack played during the performance. Using a single mobile phone video recording of a dance performance only, our system is easily usable in dance rehearsal contexts. Our method evaluates accuracy for every motion beat of the performance on a timeline giving users detailed insight into their performance. We evaluated the accuracy of our method using a dataset containing 17 video recordings of real world dance performances. Our results closely match assessments by professional dancers, indicating correct analysis by our method.Item Interactive Visual Analysis of Regional Time Series Correlation in Multi-field Climate Ensembles(The Eurographics Association, 2023) Evers, Marina; Böttinger, Michael; Linsen, Lars; Dutta, Soumya; Feige, Kathrin; Rink, Karsten; Zeckzer, DirkSpatio-temporal multi-field data resulting from ensemble simulations are commonly used in climate research to investigate possible climatic developments and their certainty. One analysis goal is the investigation of possible correlations among different spatial regions in the different fields to find regions of related behavior. We propose an interactive visual analysis approach that focuses on the analysis of correlations in spatio-temporal ensemble data. Our approach allows for finding correlations between spatial regions in different fields. Detection of clusters of strongly correlated spatial regions is supported by lower-dimensional embeddings. Then, groups can be selected and investigated in detail, e.g., to study the temporal evolution of the selected group, their Fourier spectra or the distribution of the correlations over the different ensemble members. We apply our approach to selected 2D scalar fields of a large ensemble climate simulation and demonstrate the utility of our tool with several use cases.Item Hardware de Visualização orientado para X Windows(The Eurographics Association, 2023) Pereira, J. Paulo; Costa, A. Cardoso; Ferreira, F. Nunes; José TeixeiraO "X Window System" é um dos vários sistemas de gestão de janelas disponíveis actualmente, tendo a seu favor o facto de ser suportado por um instituto de renome mundial (MIT) e por alguns fabricantes de primeiro plano (DEC, SUN, etc), de ser um sistema aberto e de permitir a implementação de terminais gráficos compatíveis, com relativa facilidade. Embora não tão "inteligente" quanto o NeWS (enquanto que o X envia comados gráficos para os terminais, o NeWS envia programas POSTSCRIPT, logo com maior compressão e funcionalidade}, tornou-se um standard de facto. A arquitectura gráfica por nós projectada é muito poderosa e foi orientada para permitir uma implementação fácil e eficiente de um servidor de X. Estes objectivos foram conseguidos através da escolha criteriosa do processador gráfico que melhor servisse os nossos objectivos, o que conduziu a um estudo comparativo de alguns de entre os dispositivos deste tipo comercialmente disponíveis.Item 3D Generative Model Latent Disentanglement via Local Eigenprojection(© 2023 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2023) Foti, Simone; Koo, Bongjin; Stoyanov, Danail; Clarkson, Matthew J.; Hauser, Helwig and Alliez, PierreDesigning realistic digital humans is extremely complex. Most data‐driven generative models used to simplify the creation of their underlying geometric shape do not offer control over the generation of local shape attributes. In this paper, we overcome this limitation by introducing a novel loss function grounded in spectral geometry and applicable to different neural‐network‐based generative models of 3D head and body meshes. Encouraging the latent variables of mesh variational autoencoders (VAEs) or generative adversarial networks (GANs) to follow the local eigenprojections of identity attributes, we improve latent disentanglement and properly decouple the attribute creation. Experimental results show that our local eigenprojection disentangled (LED) models not only offer improved disentanglement with respect to the state‐of‐the‐art, but also maintain good generation capabilities with training times comparable to the vanilla implementations of the models. Our code and pre‐trained models are available at .Item Collision Free Simplification for 2D Multi-Layered Shapes(The Eurographics Association, 2023) Gong, Xianjin; Parakkat, Amal Dev; Rohmer, Damien; Pelechano, Nuria; Liarokapis, Fotis; Rohmer, Damien; Asadipour, AliWe propose a simplification-aware untangling algorithm for 2D layered shapes stacked on each other. While the shape undergoes simplification, our approach adjusts the vertex positions to prevent collision with other layers while simultaneously maintaining the correct relative ordering and offsets between the layers. The method features a field-based representation of the shapes and extends the concept of "implicit untangling" by incorporating interleaved shape preservation through a parameterized shape-matching technique. Our approach can be plugged on top of any existing vertex-decimation approach, leveraging its localized nature to accelerate the field evaluation. Furthermore, our method can seamlessly handle an arbitrary number of stacked layers, making it a versatile solution for stacked garment simplification.Item MesoGAN: Generative Neural Reflectance Shells(© 2023 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2023) Diolatzis, Stavros; Novak, Jan; Rousselle, Fabrice; Granskog, Jonathan; Aittala, Miika; Ramamoorthi, Ravi; Drettakis, George; Hauser, Helwig and Alliez, PierreWe introduce MesoGAN, a model for generative 3D neural textures. This new graphics primitive represents mesoscale appearance by combining the strengths of generative adversarial networks (StyleGAN) and volumetric neural field rendering. The primitive can be applied to surfaces as a neural reflectance shell; a thin volumetric layer above the surface with appearance parameters defined by a neural network. To construct the neural shell, we first generate a 2D feature texture using StyleGAN with carefully randomized Fourier features to support arbitrarily sized textures without repeating artefacts. We augment the 2D feature texture with a learned height feature, which aids the neural field renderer in producing volumetric parameters from the 2D texture. To facilitate filtering, and to enable end‐to‐end training within memory constraints of current hardware, we utilize a hierarchical texturing approach and train our model on multi‐scale synthetic datasets of 3D mesoscale structures. We propose one possible approach for conditioning MesoGAN on artistic parameters (e.g. fibre length, density of strands, lighting direction) and demonstrate and discuss integration into physically based renderers.Item Interactions for Seamlessly Coupled Exploration of High-Dimensional Images and Hierarchical Embeddings(The Eurographics Association, 2023) Vieth, Alexander; Lelieveldt, Boudewijn; Eisemann, Elmar; Vilanova, Anna; Höllt, Thomas; Guthe, Michael; Grosch, ThorstenHigh-dimensional images (i.e., with many attributes per pixel) are commonly acquired in many domains, such as geosciences or systems biology. The spatial and attribute information of such data are typically explored separately, e.g., by using coordinated views of an image representation and a low-dimensional embedding of the high-dimensional attribute data. Facing ever growing image data sets, hierarchical dimensionality reduction techniques lend themselves to overcome scalability issues. However, current embedding methods do not provide suitable interactions to reflect image space exploration. Specifically, it is not possible to adjust the level of detail in the embedding hierarchy to reflect changing level of detail in image space stemming from navigation such as zooming and panning. In this paper, we propose such a mapping from image navigation interactions to embedding space adjustments. We show how our mapping applies the "overview first, details-on-demand" characteristic inherent to image exploration in the high-dimensional attribute space. We compare our strategy with regular hierarchical embedding technique interactions and demonstrate the advantages of linking image and embedding interactions through a representative use case.Item Unsupervised Template Warp Consistency for Implicit Surface Correspondences(The Eurographics Association and John Wiley & Sons Ltd., 2023) Liu, Mengya; Chhatkuli, Ajad; Postels, Janis; Gool, Luc Van; Tombari, Federico; Myszkowski, Karol; Niessner, MatthiasUnsupervised template discovery via implicit representation in a category of shapes has recently shown strong performance. At the core, such methods deform input shapes to a common template space which allows establishing correspondences as well as implicit representation of the shapes. In this work we investigate the inherent assumption that the implicit neural field optimization naturally leads to consistently warped shapes, thus providing both good shape reconstruction and correspondences. Contrary to this convenient assumption, in practice we observe that such is not the case, consequently resulting in sub-optimal point correspondences. In order to solve the problem, we re-visit the warp design and more importantly introduce explicit constraints using unsupervised sparse point predictions, directly encouraging consistency of the warped shapes. We use the unsupervised sparse keypoints in order to further condition the deformation warp and enforce the consistency of the deformation warp. Experiments in dynamic non-rigid DFaust and ShapeNet categories show that our problem identification and solution provide the new state-of-the-art in unsupervised dense correspondences.