39-Issue 2

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2632881

Browse

Now showing 1 - 20 of 50

Style-Controllable Speech-Driven Gesture Synthesis Using Normalising Flows
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Alexanderson, Simon; Henter, Gustav Eje; Kucherenko, Taras; Beskow, Jonas; Panozzo, Daniele and Assarsson, Ulf
Automatic synthesis of realistic gestures promises to transform the fields of animation, avatars and communicative agents. In off-line applications, novel tools can alter the role of an animator to that of a director, who provides only high-level input for the desired animation; a learned network then translates these instructions into an appropriate sequence of body poses. In interactive scenarios, systems for generating natural animations on the fly are key to achieving believable and relatable characters. In this paper we address some of the core issues towards these ends. By adapting a deep learning-based motion synthesis method called MoGlow, we propose a new generative model for generating state-of-the-art realistic speech-driven gesticulation. Owing to the probabilistic nature of the approach, our model can produce a battery of different, yet plausible, gestures given the same input speech signal. Just like humans, this gives a rich natural variation of motion. We additionally demonstrate the ability to exert directorial control over the output style, such as gesture level, speed, symmetry and spacial extent. Such control can be leveraged to convey a desired character personality or mood. We achieve all this without any manual annotation of the data. User studies evaluating upper-body gesticulation confirm that the generated motions are natural and well match the input speech. Our method scores above all prior systems and baselines on these measures, and comes close to the ratings of the original recorded motions. We furthermore find that we can accurately control gesticulation styles without unnecessarily compromising perceived naturalness. Finally, we also demonstrate an application of the same method to full-body gesticulation, including the synthesis of stepping motion and stance.
Interactive Modeling of Cellular Structures on Surfaces with Application to Additive Manufacturing
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Stadlbauer, Pascal; Mlakar, Daniel; Seidel, Hans-Peter; Steinberger, Markus; Zayer, Rhaleb; Panozzo, Daniele and Assarsson, Ulf
The rich and evocative patterns of natural tessellations endow them with an unmistakable artistic appeal and structural properties which are echoed across design, production, and manufacturing. Unfortunately, interactive control of such patterns-as modeled by Voronoi diagrams, is limited to the simple two dimensional case and does not extend well to freeform surfaces. We present an approach for direct modeling and editing of such cellular structures on surface meshes. The overall modeling experience is driven by a set of editing primitives which are efficiently implemented on graphics hardware. We feature a novel application for 3D printing on modern support-free additive manufacturing platforms. Our method decomposes the input surface into a cellular skeletal structure which hosts a set of overlay shells. In this way, material saving can be channeled to the shells while structural stability is channeled to the skeleton. To accommodate the available printer build volume, the cellular structure can be further split into moderately sized parts. Together with shells, they can be conveniently packed to save on production time. The assembly of the printed parts is streamlined by a part numbering scheme which respects the geometric layout of the input model.
Accurate Real-time 3D Gaze Tracking Using a Lightweight Eyeball Calibration
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Wen, Quan; Bradley, Derek; Beeler, Thabo; Park, Seonwook; Hilliges, Otmar; Yong, Jun-Hai; Xu, Feng; Panozzo, Daniele and Assarsson, Ulf
3D gaze tracking from a single RGB camera is very challenging due to the lack of information in determining the accurate gaze target from a monocular RGB sequence. The eyes tend to occupy only a small portion of the video, and even small errors in estimated eye orientations can lead to very large errors in the triangulated gaze target. We overcome these difficulties with a novel lightweight eyeball calibration scheme that determines the user-specific visual axis, eyeball size and position in the head. Unlike the previous calibration techniques, we do not need the ground truth positions of the gaze points. In the online stage, gaze is tracked by a new gaze fitting algorithm, and refined by a 3D gaze regression method to correct for bias errors. Our regression is pre-trained on several individuals and works well for novel users. After the lightweight one-time user calibration, our method operates in real time. Experiments show that our technique achieves state-of-the-art accuracy in gaze angle estimation, and we demonstrate applications of 3D gaze target tracking and gaze retargeting to an animated 3D character.
A Practical Method for Animating Anisotropic Elastoplastic Materials
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Schreck, Camille; Wojtan, Chris; Panozzo, Daniele and Assarsson, Ulf
This paper introduces a simple method for simulating highly anisotropic elastoplastic material behaviors like the dissolution of fibrous phenomena (splintering wood, shredding bales of hay) and materials composed of large numbers of irregularly-shaped bodies (piles of twigs, pencils, or cards). We introduce a simple transformation of the anisotropic problem into an equivalent isotropic one, and we solve this new ''fictitious'' isotropic problem using an existing simulator based on the material point method. Our approach results in minimal changes to existing simulators, and it allows us to re-use popular isotropic plasticity models like the Drucker-Prager yield criterion instead of inventing new anisotropic plasticity models for every phenomenon we wish to simulate.
SoftSMPL: Data-driven Modeling of Nonlinear Soft-tissue Dynamics for Parametric Humans
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Santesteban, Igor; Garces, Elena; Otaduy, Miguel A.; Casas, Dan; Panozzo, Daniele and Assarsson, Ulf
We present SoftSMPL, a learning-based method to model realistic soft-tissue dynamics as a function of body shape and motion. Datasets to learn such task are scarce and expensive to generate, which makes training models prone to overfitting. At the core of our method there are three key contributions that enable us to model highly realistic dynamics and better generalization capabilities than state-of-the-art methods, while training on the same data. First, a novel motion descriptor that disentangles the standard pose representation by removing subject-specific features; second, a neural-network-based recurrent regressor that generalizes to unseen shapes and motions; and third, a highly efficient nonlinear deformation subspace capable of representing soft-tissue deformations of arbitrary shapes. We demonstrate qualitative and quantitative improvements over existing methods and, additionally, we show the robustness of our method on a variety of motion capture databases.
Facial Expression Synthesis using a Global-Local Multilinear Framework
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Wang, Mengjiao; Bradley, Derek; Zafeiriou, Stefanos; Beeler, Thabo; Panozzo, Daniele and Assarsson, Ulf
We present a practical method to synthesize plausible 3D facial expressions for a particular target subject. The ability to synthesize an entire facial rig from a single neutral expression has a large range of applications both in computer graphics and computer vision, ranging from the efficient and cost-effective creation of CG characters to scalable data generation for machine learning purposes. Unlike previous methods based on multilinear models, the proposed approach is capable to extrapolate well outside the sample pool, which allows it to plausibly predict the identity of the target subject and create artifact free expression shapes while requiring only a small input dataset. We introduce global-local multilinear models that leverage the strengths of expression-specific and identity-specific local models combined with coarse motion estimations from a global model. Experimental results show that we achieve high-quality, plausible facial expression synthesis results for an individual that outperform existing methods both quantitatively and qualitatively.
Spectral Mollification for Bidirectional Fluorescence
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Jung, Alisa; Hanika, Johannes; Dachsbacher, Carsten; Panozzo, Daniele and Assarsson, Ulf
Fluorescent materials can shift energy between wavelengths, thereby creating bright and saturated colors both in natural and artificial materials. However, rendering fluorescence for continuous wavelengths or combined with wavelength dependent path configurations so far has only been feasible using spectral unidirectional methods. We present a regularization-based approach for supporting fluorescence in a spectral bidirectional path tracer. Our algorithm samples camera and light sub-paths with independent wavelengths, and when connecting them mollifies the BSDF at one of the connecting vertices such that it reradiates light across multiple wavelengths. We discuss arising issues such as color bias in early iterations, consistency of the method and MIS weights in the presence of spectral mollification. We demonstrate our method in scenes combining fluorescence and transport phenomena that are difficult to render with unidirectional or spectrally discrete methods.
Locally Supported Tangential Vector, n-Vector, and Tensor Fields
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Nasikun, Ahmad; Brandt, Christopher; Hildebrandt, Klaus; Panozzo, Daniele and Assarsson, Ulf
We introduce a construction of subspaces of the spaces of tangential vector, n-vector, and tensor fields on surfaces. The resulting subspaces can be used as the basis of fast approximation algorithms for design and processing problems that involve tangential fields. Important features of our construction are that it is based on a general principle, from which constructions for different types of tangential fields can be derived, and that it is scalable, making it possible to efficiently compute and store large subspace bases for large meshes. Moreover, the construction is adaptive, which allows for controlling the distribution of the degrees of freedom of the subspaces over the surface. We evaluate our construction in several experiments addressing approximation quality, scalability, adaptivity, computation times and memory requirements. Our design choices are justified by comparing our construction to possible alternatives. Finally, we discuss examples of how subspace methods can be used to build interactive tools for tangential field design and processing tasks.
Mixing Yarns and Triangles in Cloth Simulation
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Casafranca, Juan J.; Cirio, Gabriel; Rodríguez, Alejandro; Miguel, Eder; Otaduy, Miguel A.; Panozzo, Daniele and Assarsson, Ulf
This paper presents a method to combine triangle and yarn models in cloth simulation, and hence leverage their best features. The majority of a garment uses a triangle-based model, which reduces the overall computational and memory cost. Key areas of the garment use a yarn-based model, which elicits rich effects such as structural nonlinearity and plasticity. To combine both models in a seamless and robust manner, we solve two major technical challenges. We propose an enriched kinematic representation that augments triangle-based deformations with yarn-level details. Naïve enrichment suffers from kinematic redundancy, but we devise an optimal kinematic filter that allows a smooth transition between triangle and yarn models. We also introduce a preconditioner that resolves the poor conditioning produced by the extremely different inertia of triangle and yarn nodes. This preconditioner deals effectively with rank deficiency introduced by the kinematic filter. We demonstrate that mixed yarns and triangles succeed to efficiently capture rich effects in garment fit and drape.
Fast and Robust QEF Minimization using Probabilistic Quadrics
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Trettner, Philip; Kobbelt, Leif; Panozzo, Daniele and Assarsson, Ulf
Error quadrics are a fundamental and powerful building block in many geometry processing algorithms. However, finding the minimizer of a given quadric is in many cases not robust and requires a singular value decomposition or some ad-hoc regularization. While classical error quadrics measure the squared deviation from a set of ground truth planes or polygons, we treat the input data as genuinely uncertain information and embed error quadrics in a probabilistic setting (''probabilistic quadrics'') where the optimal point minimizes the expected squared error. We derive closed form solutions for the popular plane and triangle quadrics subject to (spatially varying, anisotropic) Gaussian noise. Probabilistic quadrics can be minimized robustly by solving a simple linear system-50x faster than SVD. We show that probabilistic quadrics have superior properties in tasks like decimation and isosurface extraction since they favor more uniform triangulations and are more tolerant to noise while still maintaining feature sensitivity. A broad spectrum of applications can directly benefit from our new quadrics as a drop-in replacement which we demonstrate with mesh smoothing via filtered quadrics and non-linear subdivision surfaces.
Designing Robotically-Constructed Metal Frame Structures
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Ma, Zhao; Walzer, Alexander; Schumacher, Christian; Rust, Romana; Gramazio, Fabio; Kohler, Matthias; Bächer, Moritz; Panozzo, Daniele and Assarsson, Ulf
We present a computational technique that aids with the design of structurally-sound metal frames, tailored for robotic fabrication using an existing process that integrate automated bar bending, welding, and cutting. Aligning frames with structurallyfavorable orientations, and decomposing models into fabricable units, we make the fabrication process scale-invariant, and frames globally align in an aesthetically-pleasing and structurally-informed manner. Relying on standard analysis of frames, we then co-optimize the shape and topology of bars at the local unit level. At this level, we minimize combinations of functional and aesthetic objectives under strict fabrication constraints that model the assembly of discrete sets of bent bars. We demonstrate the capabilities of our global-to-local approach on four robotically-constructed examples.
Optimizing Object Decomposition to Reduce Visual Artifacts in 3D Printing
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Filoscia, Irene; Alderighi, Thomas; Giorgi, Daniela; Malomo, Luigi; Callieri, Marco; Cignoni, Paolo; Panozzo, Daniele and Assarsson, Ulf
We propose a method for the automatic segmentation of 3D objects into parts which can be individually 3D printed and then reassembled by preserving the visual quality of the final object. Our technique focuses on minimizing the surface affected by supports, decomposing the object into multiple parts whose printing orientation is automatically chosen. The segmentation reduces the visual impact on the fabricated model producing non-planar cuts that adapt to the object shape. This is performed by solving an optimization problem that balances the effects of supports and cuts, while trying to place both in occluded regions of the object surface. To assess the practical impact of the solution, we show a number of segmented, 3D printed and reassembled objects.
Displacement-Correlated XFEM for Simulating Brittle Fracture
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Chitalu, Floyd M.; Miao, Qinghai; Subr, Kartic; Komura, Taku; Panozzo, Daniele and Assarsson, Ulf
We present a remeshing-free brittle fracture simulation method under the assumption of quasi-static linear elastic fracture mechanics (LEFM). To achieve this, we devise two algorithms. First, we develop an approximate volumetric simulation, based on the extended Finite Element Method (XFEM), to initialize and propagate Lagrangian crack-fronts. We model the geometry of fracture explicitly as a surface mesh, which allows us to generate high-resolution crack surfaces that are decoupled from the resolution of the deformation mesh. Our second contribution is a mesh cutting algorithm, which produces fragments of the input mesh using the fracture surface. We do this by directly operating on the half-edge data structures of two surface meshes, which enables us to cut general surface meshes including those of concave polyhedra and meshes with abutting concave polygons. Since we avoid triangulation for cutting, the connectivity of the resulting fragments is identical to the (uncut) input mesh except at edges introduced by the cut. We evaluate our simulation and cutting algorithms and show that they outperform state-of-the-art approaches both qualitatively and quantitatively.
Progressive Real-Time Rendering of One Billion Points Without Hierarchical Acceleration Structures
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Schütz, Markus; Mandlburger, Gottfried; Otepka, Johannes; Wimmer, Michael; Panozzo, Daniele and Assarsson, Ulf
Research in rendering large point clouds traditionally focused on the generation and use of hierarchical acceleration structures that allow systems to load and render the smallest fraction of the data with the largest impact on the output. The generation of these structures is slow and time consuming, however, and therefore ill-suited for tasks such as quickly looking at scan data stored in widely used unstructured file formats, or to immediately display the results of point-cloud processing tasks. We propose a progressive method that is capable of rendering any point cloud that fits in GPU memory in real time, without the need to generate hierarchical acceleration structures in advance. Our method supports data sets with a large amount of attributes per point, achieves a load performance of up to 100 million points per second, displays already loaded data in real time while remaining data is still being loaded, and is capable of rendering up to one billion points using an on-the-fly generated shuffled vertex buffer as its data structure, instead of slow-to-generate hierarchical structures. Shuffling is done during loading in order to allow efficiently filling holes with random subsets, which leads to a higher quality convergence behavior.
RGB2AO: Ambient Occlusion Generation from RGB Images
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Inoue, Naoto; Ito, Daichi; Hold-Geoffroy, Yannick; Mai, Long; Price, Brian; Yamasaki, Toshihiko; Panozzo, Daniele and Assarsson, Ulf
We present RGB2AO, a novel task to generate ambient occlusion (AO) from a single RGB image instead of screen space buffers such as depth and normal. RGB2AO produces a new image filter that creates a non-directional shading effect that darkens enclosed and sheltered areas. RGB2AO aims to enhance two 2D image editing applications: image composition and geometryaware contrast enhancement. We first collect a synthetic dataset consisting of pairs of RGB images and AO maps. Subsequently, we propose a model for RGB2AO by supervised learning of a convolutional neural network (CNN), considering 3D geometry of the input image. Experimental results quantitatively and qualitatively demonstrate the effectiveness of our model.
Unified Neural Encoding of BTFs
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Rainer, Gilles; Ghosh, Abhijeet; Jakob, Wenzel; Weyrich, Tim; Panozzo, Daniele and Assarsson, Ulf
Realistic rendering using discrete reflectance measurements is challenging, because arbitrary directions on the light and view hemispheres are queried at render time, incurring large memory requirements and the need for interpolation. This explains the desire for compact and continuously parametrized models akin to analytic BRDFs; however, fitting BRDF parameters to complex data such as BTF texels can prove challenging, as models tend to describe restricted function spaces that cannot encompass real-world behavior. Recent advances in this area have increasingly relied on neural representations that are trained to reproduce acquired reflectance data. The associated training process is extremely costly and must typically be repeated for each material. Inspired by autoencoders, we propose a unified network architecture that is trained on a variety of materials, and which projects reflectance measurements to a shared latent parameter space. Similarly to SVBRDF fitting, real-world materials are represented by parameter maps, and the decoder network is analog to the analytic BRDF expression (also parametrized on light and view directions for practical rendering application). With this approach, encoding and decoding materials becomes a simple matter of evaluating the network. We train and validate on BTF datasets of the University of Bonn, but there are no prerequisites on either the number of angular reflectance samples, or the sample positions. Additionally, we show that the latent space is well-behaved and can be sampled from, for applications such as mipmapping and texture synthesis.
Robust Shape Collection Matching and Correspondence from Shape Differences
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Cohen, Aharon; Ben-Chen, Mirela; Panozzo, Daniele and Assarsson, Ulf
We propose a method to automatically match two shape collections with a similar shape space structure, e.g. two characters in similar poses, and compute the inter-maps between the collections. Given the intra-maps in each collection, we extract the corresponding shape difference operators, and use them to construct an embedding of the shape space of each collection. We then align the two shape spaces, and use the knowledge gained from the alignment to compute the inter-maps. Unlike existing approaches for collection alignment, our method is applicable to small and large collections alike, and requires no parameter tuning. Furthermore, unlike most approaches for non-isometric correspondence, our method uses solely the variation within the collection to extract the inter-maps, and therefore does not require landmarks, descriptors or any additional input. We demonstrate that we achieve high matching accuracy rates, and compute high quality maps on non-isometric shapes, which compare favorably with automatic state-of-the-art methods for non-isometric shape correspondence.
Persistence Analysis of Multi-scale Planar Structure Graph in Point Clouds
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Lejemble, Thibault; Mura, Claudio; Barthe, Loïc; Mellado, Nicolas; Panozzo, Daniele and Assarsson, Ulf
Modern acquisition techniques generate detailed point clouds that sample complex geometries. For instance, we are able to produce millimeter-scale acquisition of whole buildings. Processing and exploring geometrical information within such point clouds requires scalability, robustness to acquisition defects and the ability to model shapes at different scales. In this work, we propose a new representation that enriches point clouds with a multi-scale planar structure graph. We define the graph nodes as regions computed with planar segmentations at increasing scales and the graph edges connect regions that are similar across scales. Connected components of the graph define the planar structures present in the point cloud within a scale interval. For instance, with this information, any point is associated to one or several planar structures existing at different scales. We then use topological data analysis to filter the graph and provide the most prominent planar structures. Our representation naturally encodes a large range of information. We show how to efficiently extract geometrical details (e.g. tiles of a roof), arrangements of simple shapes (e.g. steps and mean ramp of a staircase), and large-scale planar proxies (e.g. walls of a building) and present several interactive tools to visualize, select and reconstruct planar primitives directly from raw point clouds. The effectiveness of our approach is demonstrated by an extensive evaluation on a variety of input data, as well as by comparing against state-of-the-art techniques and by showing applications to polygonal mesh reconstruction.
Prefilters for Sharp Image Display
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Rocha, Luís Cláudio Gouveia; Oliveira, Manuel M.; Gastal, Eduardo S. L.; Panozzo, Daniele and Assarsson, Ulf
In this paper we use a simplified model of the human visual system to explain why humans tend do prefer ''sharpened'' digital images. From this model we then derive a family of image prefilters specifically adapted to viewing conditions and user preference, allowing for the trade-off between ringing and aliasing while maximizing image sharpness. We discuss how our filters can be applied in a variety of situations ranging from Monte Carlo rendering to image downscaling, and we show how they consistently give sharper results while having an efficient implementation and ease of use (there are no free parameters that require manual tuning). We demonstrate the effectiveness of our simple sharp prefilters through a user study that indicates a clear preference to our approach compared to the state-of-the-art.
Interactive Meso-scale Simulation of Skyscapes
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Vimont, Ulysse; Gain, James; Lastic, Maud; Cordonnier, Guillaume; Abiodun, Babatunde; Cani, Marie-Paule; Panozzo, Daniele and Assarsson, Ulf
Although an important component of natural scenes, the representation of skyscapes is often relatively simplistic. This can be largely attributed to the complexity of the thermodynamics underpinning cloud evolution and wind dynamics, which make interactive simulation challenging.We address this problem by introducing a novel layered model that encompasses both terrain and atmosphere, and supports efficient meteorological simulations. The vertical and horizontal layer resolutions can be tuned independently, while maintaining crucial inter-layer thermodynamics, such as convective circulation and land-air transfers of heat and moisture. In addition, we introduce a cloud-form taxonomy for clustering, classifying and upsampling simulation cells to enable visually plausible, finely-sampled volumetric rendering. As our results demonstrate, this pipeline allows interactive simulation followed by up-sampled rendering of extensive skyscapes with dynamic clouds driven by consistent wind patterns. We validate our method by reproducing characteristic phenomena such as diurnal shore breezes, convective cells that contribute to cumulus cloud formation, and orographic effects from moist air driven upslope.

Browse

Browsing 39-Issue 2 by Issue Date

Results Per Page

Sort Options