We introduce a Delaunay-based algorithm for reconstructing the underlying surface of a given set of unstructured points in 3D. The implementation is very simple, and it is designed to work in a parameter-free manner. The solution builds upon the fact that in the continuous case, a closed surface separates the set of maximal empty balls (medial balls) into an interior and exterior. Based on discrete input samples, our reconstructed surface consists of the interface between Voronoi balls, which approximate the interior and exterior medial balls. An initial set of Voronoi balls is iteratively processed, merging Voronoi-ball pairs if they fulfil an overlapping error criterion. Our complete open-source reconstruction pipeline performs up to two quick linear-time passes on the Delaunay complex to output the surface, making it an order of magnitude faster than the state of the art while being competitive in memory usage and often superior in quality. We propose two variants (local and global), which are carefully designed to target two different reconstruction scenarios for watertight surfaces from accurate or noisy samples, as well as real-world scanned data sets, exhibiting noise, outliers, and large areas of missing data. The results of the global variant are, by definition, watertight, suitable for numerical analysis and various applications (e.g., 3D printing). Compared to classical Delaunay-based reconstruction techniques, our method is highly stable and robust to noise and outliers, evidenced via various experiments, including on real-world data with challenges such as scan shadows, outliers, and noise, even without additional preprocessing.@en

The need to understand the structure of hierarchical or high-dimensional data is present in a variety of fields. Hyperbolic spaces have proven to be an important tool for embedding computations and analysis tasks as their non-linear nature lends itself well to tree or graph data. Subsequently, they have also been used in the visualization of high-dimensional data, where they exhibit increased embedding performance. However, none of the existing dimensionality reduction methods for embedding into hyperbolic spaces scale well with the size of the input data. That is because the embeddings are computed via iterative optimization schemes and the computation cost of every iteration is quadratic in the size of the input. Furthermore, due to the non-linear nature of hyperbolic spaces, euclidean acceleration structures cannot directly be translated to the hyperbolic setting. This article introduces the first acceleration structure for hyperbolic embeddings, building upon a polar quadtree. We compare our approach with existing methods and demonstrate that it computes embeddings of similar quality in significantly less time. Implementation and scripts for the experiments can be found at https://graphics.tudelft.nl/accelerating-hyperbolic-tsne .@en

The display coefficients that produce the signal emitted by a light field display are usually calculated to approximate the radiance over a set of sampled rays in the light field space. However, not all information contained in the light field signal is of equal importance to an observer. We propose a retinal pre-filtering of the light field samples that takes into account the image formation process of the observer to determine display coefficients that will ultimately produce better retinal images for a range of focus distances. We demonstrate a significant increase in image definition without changing the display resolution.@en

Exploration and analysis of high-dimensional data are important tasks in many fields that produce large and complex data, like the financial sector, systems biology, or cultural heritage. Tailor-made visual analytics software is developed for each specific application, limiting their applicability in other fields. However, as diverse as these fields are, their characteristics and requirements for data analysis are conceptually similar. Many applications share abstract tasks and data types and are often constructed with similar building blocks. Developing such applications, even when based mostly on existing building blocks, requires significant engineering efforts. We developed ManiVault, a flexible and extensible open-source visual analytics framework for analyzing high-dimensional data. The primary objective of ManiVault is to facilitate rapid prototyping of visual analytics workflows for visualization software developers and practitioners alike. ManiVault is built using a plugin-based architecture that offers easy extensibility. While our architecture deliberately keeps plugins self-contained, to guarantee maximum flexibility and re-usability, we have designed and implemented a messaging API for tight integration and linking of modules to support common visual analytics design patterns. We provide several visualization and analytics plugins, and ManiVault's API makes the integration of new plugins easy for developers. ManiVault facilitates the distribution of visualization and analysis pipelines and results for practitioners through saving and reproducing complete application states. As such, ManiVault can be used as a communication tool among researchers to discuss workflows and results. A copy of this paper and all supplemental material is available at osf.io/9k6jw, and source code at github.com/ManiVaultStudio.

@en

Recovering spatially-varying materials from a single photograph of a surface is inherently ill-posed, making the direct application of a gradient descent on the reflectance parameters prone to poor minima. Recent methods leverage deep learning either by directly regressing reflectance parameters using feed-forward neural networks or by learning a latent space of SVBRDFs using encoder-decoder or generative adversarial networks followed by a gradient-based optimization in latent space. The former is fast but does not account for the likelihood of the prediction, i.e., how well the resulting reflectance explains the input image. The latter provides a strong prior on the space of spatially-varying materials, but this prior can hinder the reconstruction of images that are too different from the training data. Our method combines the strengths of both approaches. We optimize reflectance parameters to best reconstruct the input image using a recurrent neural network, which iteratively predicts how to update the reflectance parameters given the gradient of the reconstruction likelihood. By combining a learned prior with a likelihood measure, our approach provides a maximum a posteriori estimate of the SVBRDF. Our evaluation shows that this learned gradient-descent method achieves state-of-the-art performance for SVBRDF estimation on synthetic and real images.@en

The contour depth methodology enables non-parametric summarization of contour ensembles by extracting their representatives, confidence bands, and outliers for visualization (via contour boxplots) and robust downstream procedures. We address two shortcomings of these methods. Firstly, we significantly expedite the computation and recomputation of Inclusion Depth (ID), introducing a linear-time algorithm for epsilon ID, a variant used for handling ensembles with contours with multiple intersections. We also present the inclusion matrix, which contains the pairwise inclusion relationships between contours, and leverage it to accelerate the recomputation of ID. Secondly, extending beyond the single distribution assumption, we present the Relative Depth (ReD), a generalization of contour depth for ensembles with multiple modes. Building upon the linear-time eID, we introduce CDclust, a clustering algorithm that untangles ensemble modes of variation by optimizing ReD. Synthetic and real datasets from medical image segmentation and meteorological forecasting showcase the speed advantages, illustrate the use case of progressive depth computation and enable non-parametric multimodal analysis. To promote research and adoption, we offer the contour-depth Python package.

@en

We introduce a geometric multigrid method for solving linear systems arising from variational problems on surfaces in geometry processing, Gravo MG. Our scheme uses point clouds as a reduced representation of the levels of the multigrid hierarchy to achieve a fast hierarchy construction and to extend the applicability of the method from triangle meshes to other surface representations like point clouds, nonmanifold meshes, and polygonal meshes. To build the prolongation operators, we associate each point of the hierarchy to a triangle constructed from points in the next coarser level. We obtain well-shaped candidate triangles by computing graph Voronoi diagrams centered around the coarse points and determining neighboring Voronoi cells. Our selection of triangles ensures that the connections of each point to points at adjacent coarser and finer levels are balanced in the tangential directions. As a result, we obtain sparse prolongation matrices with three entries per row and fast convergence of the solver. Code is available at https://graphics.tudelft.nl/gravo_mg.@en

High-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.@en

We introduce an approach for converting pixel art into high-quality vector images. While much progress has been made on automatic conversion, there is an inherent ambiguity in pixel art, which can lead to a mismatch with the artist's original intent. Further, there is room for incorporating aesthetic preferences during the conversion. In consequence, this work introduces an interactive framework to enable users to guide the conversion process towards high-quality vector illustrations. A key idea of the method is to cast the conversion process into a spring-system optimization that can be influenced by the user. Hereby, it is possible to resolve various ambiguities that cannot be handled by an automatic algorithm.

@en

Dynamic Neural Radiance Fields (NeRFs) achieve remarkable visual quality when synthesizing novel views of time-evolving 3D scenes. However, the common reliance on backward deformation fields makes reanimation of the captured object poses challenging. Moreover, the state of the art dynamic models are often limited by low visual fidelity, long reconstruction time or specificity to narrow application domains. In this paper, we present a novel method utilizing a point-based representation and Linear Blend Skinning (LBS) to jointly learn a Dynamic NeRF and an associated skeletal model from even sparse multi-view video. Our forward-warping approach achieves state-of-the-art visual fidelity when synthesizing novel views and poses while significantly reducing the necessary learning time when compared to existing work. We demonstrate the versatility of our representation on a variety of articulated objects from common datasets and obtain reposable 3D reconstructions without the need of object-specific skeletal templates. Code will be made available at https://github.com/lukasuz/Articulated-Point-NeRF.@en

Spectral rendering is a crucial solution for photorealistic rendering. However, most available texture assets are RGB-only, and access to spectral content is limited. Uplifting methods that recover full spectral representations from RGB inputs have therefore received much attention. Yet, most methods are deterministic, while, in reality, there is no one-to-one mapping. As a consequence, the appearance of uplifted textures is fully determined under all illuminants. Hereby, metamers, which are materials with differing spectral responses that appear identical under a specific illumination, are excluded. We propose a method which makes this uplifting process controllable. Hereby, a user can define texture appearance under various lighting conditions, leading to a greatly increased flexibility for content design. Our method determines the space of possible metameric manipulations and enables interactive adjustments, while maintaining a set of user-specified appearance constraints. To achieve this goal, we formulate the problem as a constrained optimization, building upon an interpolation scheme and data-based reflectance generation, which maintain plausibility. Besides its value for artistic control, our solution is lightweight and can be executed on the fly, which keeps its memory consumption low and makes it easy to integrate into existing frameworks.

@en

Disruptive technology has become an integral part of our lives, and it has brought about a significant transformation in the way we interact, communicate, and share information, also in the field of education. Innovation in technology needs to be based on ethics and values of the intended result. As the use of disruptive technology continues to grow, so does the need to understand and consider ethical and value dimensions. How can disruptive technology be developed and used in an ethical way for learning and teaching? What are the values the development and implementation of disruptive technology for education should take into account? How to measure and evaluate values and ethical dimensions of disruptive technology for educational purposes? Are some of the important questions to address. This workshop paper presents a method for eliciting values and ethical dimensions of learning scenarios with disruptive technologies in vocational and higher education settings and illustrates its implementation in the context of the Horizon Europe e-DIPLOMA project. The workshop method, combining value cards and learning scenarios with disruptive technologies, was implemented in seven different countries. The preliminary results of the workshops are presented. The method has the potential to draw peoples’ attention to prospective value concerns and ethical aspects necessary for understanding and acknowledging the consequence of implementing disruptive technologies in education.

@en

Sparse Voxel Directed Acyclic Graphs (SVDAGs) are an efficient solution for storing high-resolution voxel geometry. Recently, algorithms for the interactive modification of SVDAGs have been proposed that maintain the compressed geometric representation. Nevertheless, voxel attributes, such as colours, require an uncompressed storage, which can result in high memory usage over the course of the application. The reason is the high cost of existing attribute-compression schemes which remain unfit for interactive applications. In this paper, we introduce two attribute compression methods (lossless and lossy), which enable the interactive editing of compressed high-resolution voxel scenes including attributes.

@en

We present a method to capture the 7-dimensional light field structure, and translate it into perceptually-relevant information. Our spectral cubic illumination method quantifies objective correlates of perceptually relevant diffuse and directed light components, including their variations over time, space, in color and direction, and the environment’s response to sky and sunlight. We applied it “in the wild”, capturing how light on a sunny day differs between light and shadow, and how light varies over sunny and cloudy days. We discuss the added value of our method for capturing nuanced lighting effects on scene and object appearance, such as chromatic gradients.

@en

Deep learning has improved vanishing point detection in images. Yet, deep networks require expensive annotated datasets trained on costly hardware and do not generalize to even slightly different domains, and minor problem variants. Here, we address these issues by injecting deep vanishing point detection networks with prior knowledge. This prior knowledge no longer needs to be learned from data, saving valuable annotation efforts and compute, unlocking realistic few-sample scenarios, and reducing the impact of domain changes. Moreover, the interpretability of the priors allows to adapt deep networks to minor problem variations such as switching between Manhattan and non-Manhattan worlds. We seamlessly incorporate two geometric priors: (i) Hough Transform -- mapping image pixels to straight lines, and (ii) Gaussian sphere -- mapping lines to great circles whose intersections denote vanishing points. Experimentally, we ablate our choices and show comparable accuracy to existing models in the large-data setting. We validate our model's improved data efficiency, robustness to domain changes, adaptability to non-Manhattan settings.@en

Screen-space ambient occlusion (SSAO) shows high efficiency and is widely used in real-time 3D applications. However, using SSAO algorithms in stereo rendering can lead to inconsistencies due to the differences in the screen-space information captured by the left and right eye. This will affect the perception of the scene and may be a source of viewer discomfort. In this paper, we show that the raw obscurance estimation part and subsequent filtering are both sources of inconsistencies. We developed a screen-space method involving both views in conjunction, leading to a stereo-aware raw obscurance estimation method and a stereo-aware bilateral filter. The results show that our method reduces stereo inconsistencies to a level comparable to geometry-based AO solutions, while maintaining the performance benefits of a screen-space approach.

@en

Plastic pollution in the sea is an environmental hazard, negatively impacts marine life, and causes economic damage all over the world. It is estimated that each year 8 million tonnes of plastic are deposited in seas, the vast majority coming from rivers. In recent years, publicly available satellite imagery has been used to attempt to track floating plastic debris, using specialized hand-crafted features. In this work, we present an automatic learning approach based on satellite imagery that can detect floating plastic debris in rivers with high precision. This approach is based on well-proven image segmentation architectures, U-Net (RonnebeRger et al., 2015) and DeeplabV3+ (Chen et al., 2018), which we adapt to process high-dimensional multispectral images. To train and test the approach, we also present a dataset of images from different rivers around the world containing floating plastic debris, which is a key step to creating an automated learning solution. We test the predictive accuracy of our network, showing that our approach can correctly identify floating debris in images from regions not seen in the training set. Our results also show that a more extensive labeled dataset is necessary to generalize the approach to some types of rivers. Furthermore, we also demonstrate how our solution can also be used to monitor single areas over time to understand and predict floating debris accumulation.

@en

Learning from 3D point-cloud data has rapidly gained momentum, motivated by the success of deep learning on images and the increased availability of 3D~data. In this paper, we aim to construct anisotropic convolution layers that work directly on the surface derived from a point cloud. This is challenging because of the lack of a global coordinate system for tangential directions on surfaces. We introduce DeltaConv, a convolution layer that combines geometric operators from vector calculus to enable the construction of anisotropic filters on point clouds. Because these operators are defined on scalar- and vector-fields, we separate the network into a scalar- and a vector-stream, which are connected by the operators. The vector stream enables the network to explicitly represent, evaluate, and process directional information. Our convolutions are robust and simple to implement and match or improve on state-of-the-art approaches on several benchmarks, while also speeding up training and inference.@en