39-Issue 8

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2632936

Browse

Now showing 1 - 20 of 20

ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Xie, Zhaoming; Ling, Hung Yu; Kim, Nam Hee; Panne, Michiel van de; Bender, Jan and Popa, Tiberiu
Humans are highly adept at walking in environments with foot placement constraints, including stepping-stone scenarios where footstep locations are fully constrained. Finding good solutions to stepping-stone locomotion is a longstanding and fundamental challenge for animation and robotics. We present fully learned solutions to this difficult problem using reinforcement learning. We demonstrate the importance of a curriculum for efficient learning and evaluate four possible curriculum choices compared to a non-curriculum baseline. Results are presented for a simulated humanoid, a realistic bipedal robot simulation and a monster character, in each case producing robust, plausible motions for challenging stepping stone sequences and terrains.
A Bending Model for Nodal Discretizations of Yarn-Level Cloth
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Pizana, José María; Rodríguez, Alejandro; Cirio, Gabriel; Otaduy, Miguel A.; Bender, Jan and Popa, Tiberiu
To deploy yarn-level cloth simulations in production environments, it is paramount to design very efficient implementations, which mitigate the cost of the extremely high resolution. To this end, nodal discretizations aligned with the regularity of the fabric structure provide an optimal setting for efficient GPU implementations. However, nodal discretizations complicate the design of robust and controllable bending. In this paper, we address this challenge, and propose a model of bending that is both robust and controllable, and employs only nodal degrees of freedom. We extract information of yarn and fabric orientation implicitly from the nodal degrees of freedom, with no need to augment the model explicitly. But most importantly, and unlike previous formulations that use implicit orientations, the computation of bending forces bears no overhead with respect to other nodal forces such as stretch. This is possible by tracking optimal orientations efficiently. We demonstrate the impact of our bending model in examples with controllable anisotropy, as well as ironing, wrinkling, and plasticity.
Cloth and Skin Deformation with a Triangle Mesh Based Convolutional Neural Network
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Chentanez, Nuttapong; Macklin, Miles; Müller, Matthias; Jeschke, Stefan; Kim, Tae-Yong; Bender, Jan and Popa, Tiberiu
We introduce a triangle mesh based convolutional neural network. The proposed network structure can be used for problems where input and/or output are defined on a manifold triangle mesh with or without boundary. We demonstrate its applications in cloth upsampling, adding back details to Principal Component Analysis (PCA) compressed cloth, regressing clothing deformation from character poses, and regressing hand skin deformation from bones' joint angles. The data used for training in this work are generated from high resolution extended position based dynamics (XPBD) physics simulations with small time steps and high iteration counts and from an offline FEM simulator, but it can come from other sources. The inference time of our prototype implementation, depending on the mesh resolution and the network size, can provide between 4 to 134 times faster than a GPU based simulator. The inference also only needs to be done for meshes currently visible by the camera.
Detailed Rigid Body Simulation with Extended Position Based Dynamics
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Müller, Matthias; Macklin, Miles; Chentanez, Nuttapong; Jeschke, Stefan; Kim, Tae-Yong; Bender, Jan and Popa, Tiberiu
We present a rigid body simulation method that can resolve small temporal and spatial details by using a quasi explicit integration scheme that is unconditionally stable. Traditional rigid body simulators linearize constraints because they operate on the velocity level or solve the equations of motion implicitly thereby freezing the constraint directions for multiple iterations. Our method always works with the most recent constraint directions. This allows us to trace high speed motion of objects colliding against curved geometry, to reduce the number of constraints, to increase the robustness of the simulation, and to simplify the formulation of the solver. In this paper we provide all the details to implement a fully fledged rigid body solver that handles contacts, a variety of joint types and the interaction with soft objects.
Distant Collision Response in Rigid Body Simulations
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Coevoet, Eulalie; Andrews, Sheldon; Relles, Denali; Kry, Paul G.; Bender, Jan and Popa, Tiberiu
We use a finite element model to predict the vibration response of objects in a rigid body simulation, such that rigid objects are augmented to provide a plausible elastic collision response between distant objects due to vibration. We start with a generalized eigenvalue decomposition of the elastic model to precompute a response to an impact at any point on an elastic object with fixed boundary conditions. Then, given a collision between objects, we generate an approximate response impulse to distribute to other objects already in contact with the colliding bodies. This can lead to distant impacts causing an object to slip, or a delicate stack of objects to fall. We also use a geodesic distance based spatial attenuation approximation for travelling waves in objects to respond to an impact at one contact with an impulse at other locations. This response ultimately allows a long distance relationship between contacts, both across a single object being struck, but also traversing the contact graph of a larger collection of objects. We qualitatively validate our approach with a ground truth simulation, and demonstrate a number of scenarios where a long distance relationship between contacts is valuable.
A Divergence-free Mixture Model for Multiphase Fluids
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Jiang, Yuntao; Li, Chenfeng; Deng, Shujie; Hu, Shi-Min; Bender, Jan and Popa, Tiberiu
We present a novel divergence free mixture model for multiphase flows and the related fluid-solid coupling. The new mixture model is built upon a volume-weighted mixture velocity so that the divergence free condition is satisfied for miscible and immiscible multiphase fluids. The proposed mixture velocity can be solved efficiently by adapted single phase incompressible solvers, allowing for larger time steps and smaller volume deviations. Besides, the drift velocity formulation is corrected to ensure mass conservation during the simulation. The new approach increases the accuracy of multiphase fluid simulation by several orders. The capability of the new divergence-free mixture model is demonstrated by simulating different multiphase flow phenomena including mixing and unmixing of multiple fluids, fluid-solid coupling involving deformable solids and granular materials.
Effective Time Step Restrictions for Explicit MPM Simulation
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Sun, Yunxin; Shinar, Tamar; Schroeder, Craig; Bender, Jan and Popa, Tiberiu
Time steps for explicit MPM simulation in computer graphics are often selected by trial and error due to the challenges in automatically selecting stable time step sizes. Our time integration scheme uses time step restrictions that take into account forces, collisions, and even grid-to-particle transfers calculated near the end of the time step. We propose a novel set of time step restrictions that allow a time step to be selected that is stable, efficient to compute, and not too far from optimal. We derive the general solution for the sound speed in nonlinear isotropic hyperelastic materials, which we use to enforce the classical CFL time step restriction. We identify a single-particle instability in explicit MPM integration and propose a corresponding time step restriction in the fluid case. We also propose a reflection-based boundary condition for domain walls that supports separation and accurate Coulomb friction while preventing particles from penetrating the domain walls.
Efficient 2D Simulation on Moving 3D Surfaces
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Morgenroth, Dieter; Reinhardt, Stefan; Weiskopf, Daniel; Eberhardt, Bernhard; Bender, Jan and Popa, Tiberiu
We present a method to simulate fluid flow on evolving surfaces, e.g., an oil film on a water surface. Given an animated surface (e.g., extracted from a particle-based fluid simulation) in three-dimensional space, we add a second simulation on this base animation. In general, we solve a partial differential equation (PDE) on a level set surface obtained from the animated input surface. The properties of the input surface are transferred to a sparse volume data structure that is then used for the simulation. We introduce one-way coupling strategies from input properties to our simulation and we add conservation of mass and momentum to existing methods that solve a PDE in a narrow-band using the Closest Point Method. In this way, we efficiently compute high-resolution 2D simulations on coarse input surfaces. Our approach helps visual effects creators easily integrate a workflow to simulate material flow on evolving surfaces into their existing production pipeline.
Fully Convolutional Graph Neural Networks for Parametric Virtual Try-On
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Vidaurre, Raquel; Santesteban, Igor; Garces, Elena; Casas, Dan; Bender, Jan and Popa, Tiberiu
We present a learning-based approach for virtual try-on applications based on a fully convolutional graph neural network. In contrast to existing data-driven models, which are trained for a specific garment or mesh topology, our fully convolutional model can cope with a large family of garments, represented as parametric predefined 2D panels with arbitrary mesh topology, including long dresses, shirts, and tight tops. Under the hood, our novel geometric deep learning approach learns to drape 3D garments by decoupling the three different sources of deformations that condition the fit of clothing: garment type, target body shape, and material. Specifically, we first learn a regressor that predicts the 3D drape of the input parametric garment when worn by a mean body shape. Then, after a mesh topology optimization step where we generate a sufficient level of detail for the input garment type, we further deform the mesh to reproduce deformations caused by the target body shape. Finally, we predict fine-scale details such as wrinkles that depend mostly on the garment material. We qualitatively and quantitatively demonstrate that our fully convolutional approach outperforms existing methods in terms of generalization capabilities and memory requirements, and therefore it opens the door to more general learning-based models for virtual try-on applications.
Higher-Order Time Integration for Deformable Solids
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Löschner, Fabian; Longva, Andreas; Jeske, Stefan; Kugelstadt, Tassilo; Bender, Jan; Bender, Jan and Popa, Tiberiu
Visually appealing and vivid simulations of deformable solids represent an important aspect of physically based computer animation. For the temporal discretization, it is customary in computer animation to use first-order accurate integration methods, such as Backward Euler, due to their simplicity and robustness. Although there is notable research on second-order methods, their use is not widespread. Many of these well-known methods have significant drawbacks such as severe numerical damping or scene-dependent time step restrictions to ensure stability. In this paper, we discuss the most relevant requirements on such methods in computer animation and motivate the interest beyond first-order accuracy. Keeping these requirements in mind, we investigate several promising methods from the families of diagonally implicit Runge-Kutta (DIRK) and Rosenbrock methods which currently do not appear to have considerable popularity in this field. We show that the usage of such methods improves the visual quality of physical animations. In addition, we demonstrate that they allow distinctly more control over damping at lower computational cost than classical methods. As part of our theoretical contribution, we review aspects of simulations that are often considered more intricate with higher-order methods, such as contact handling. To this end, we derive an implicit linearized contact model based on a predictor-corrector approach that leads to consistent behavior with higher-order integrators as predictors. Our contact model is well suited for the simulation of stiff, nonlinear materials with the integration methods presented in this paper and more common methods such as Backward Euler alike.
Interactive Sound Propagation For Dynamic Scenes Using 2d Wave Simulation
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Rosen, Matthew; Godin, Keith W.; Raghuvanshi, Nikunj; Bender, Jan and Popa, Tiberiu
We present a technique to model wave-based sound propagation to complement visual animation in fully dynamic scenes. We employ 2D wave simulation that captures geometry-based diffraction effects such as obstruction, reverberation, and directivity of perceptually-salient initial sound at the source and listener. We show real-time performance on a single CPU core on modestly-sized scenes that are nevertheless topologically complex. Our key ideas are to exploit reciprocity and use a perceptual encoding and rendering framework. These allow the use of low-frequency finite-difference simulations on static scene snapshots. Our results show plausible audio variation that remains robust to motion and geometry changes. We suggest that wave solvers can be a practical approach to real-time dynamic acoustics. We share the complete C++ code of our ''Planeverb'' system.
Intuitive Facial Animation Editing Based On A Generative RNN Framework
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Berson, Eloïse; Soladié, Catherine; Stoiber, Nicolas; Bender, Jan and Popa, Tiberiu
For the last decades, the concern of producing convincing facial animation has garnered great interest, that has only been accelerating with the recent explosion of 3D content in both entertainment and professional activities. The use of motion capture and retargeting has arguably become the dominant solution to address this demand. Yet, despite high level of quality and automation performance-based animation pipelines still require manual cleaning and editing to refine raw results, which is a time- and skill-demanding process. In this paper, we look to leverage machine learning to make facial animation editing faster and more accessible to non-experts. Inspired by recent image inpainting methods, we design a generative recurrent neural network that generates realistic motion into designated segments of an existing facial animation, optionally following userprovided guiding constraints. Our system handles different supervised or unsupervised editing scenarios such as motion filling during occlusions, expression corrections, semantic content modifications, and noise filtering. We demonstrate the usability of our system on several animation editing use cases.
Latent Space Subdivision: Stable and Controllable Time Predictions for Fluid Flow
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Wiewel, Steffen; Kim, Byungsoo; Azevedo, Vinicius; Solenthaler, Barbara; Thuerey, Nils; Bender, Jan and Popa, Tiberiu
We propose an end-to-end trained neural network architecture to robustly predict the complex dynamics of fluid flows with high temporal stability. We focus on single-phase smoke simulations in 2D and 3D based on the incompressible Navier-Stokes (NS) equations, which are relevant for a wide range of practical problems. To achieve stable predictions for long-term flow sequences with linear execution times, a convolutional neural network (CNN) is trained for spatial compression in combination with a temporal prediction network that consists of stacked Long Short-Term Memory (LSTM) layers. Our core contribution is a novel latent space subdivision (LSS) to separate the respective input quantities into individual parts of the encoded latent space domain. As a result, this allows to distinctively alter the encoded quantities without interfering with the remaining latent space values and hence maximizes external control. By selectively overwriting parts of the predicted latent space points, our proposed method is capable to robustly predict long-term sequences of complex physics problems, like the flow of fluids. In addition, we highlight the benefits of a recurrent training on the latent space creation, which is performed by the spatial compression network. Furthermore, we thoroughly evaluate and discuss several different components of our method.
Linear Time Stable PD Controllers for Physics-based Character Animation
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Yin, Zhiqi; Yin, KangKang; Bender, Jan and Popa, Tiberiu
In physics-based character animation, Proportional-Derivative (PD) controllers are commonly used for tracking reference motions in motor control tasks. Stable PD (SPD) controllers significantly improve the numerical stability of traditional PD controllers and support large gains and large integration time steps during simulation [TLT11]. For an articulated rigid body system with n degrees of freedom, all SPD implementations to date, however, use an O(n3) dense matrix factorization based method. In this paper, we propose a linear time algorithm for SPD computation, which is based on Featherstone's forward dynamics formulation for articulated rigid body systems in generalized coordinates [Fea14]. We demonstrate the performance advantage of our algorithm by comparing with both the conventional dense matrix factorization based method and an alternative sparse matrix factorization based method.We show that the proposed algorithm provides superior stability when controlling complex models at large time steps. We further demonstrate that our algorithm can improve the learning speed and quality of a Deep Reinforcement Learning (DRL) system for physics-based character animation.
Making Procedural Water Waves Boundary-aware
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Jeschke, Stefan; Hafner, Christian; Chentanez, Nuttapong; Macklin, Miles; Müller-Fischer, Matthias; Wojtan, Chris; Bender, Jan and Popa, Tiberiu
The ''procedural'' approach to animating ocean waves is the dominant algorithm for animating larger bodies of water in interactive applications as well as in off-line productions - it provides high visual quality with a low computational demand. In this paper, we widen the applicability of procedural water wave animation with an extension that guarantees the satisfaction of boundary conditions imposed by terrain while still approximating physical wave behavior. In combination with a particle system that models wave breaking, foam, and spray, this allows us to naturally model waves interacting with beaches and rocks. Our system is able to animate waves at large scales at interactive frame rates on a commodity PC.
Particle-based Liquid Control using Animation Templates
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Schoentgen, Arnaud; Poulin, Pierre; Darles, Emmanuelle; Meseure, Philippe; Bender, Jan and Popa, Tiberiu
It is notoriously difficult for artists to control liquids while generating plausible animations. We introduce a new liquid control tool that allows users to load, transform, and apply precomputed liquid simulation templates in a scene in order to control a particle-based simulation. Each template instance generates control forces that drive the global simulated liquid to locally reproduce the templated liquid behavior. Our system is augmented with a variable proportion of temporary particles to help efficiently reproduce the templated liquid density, with fewer requirements on the surrounding environment. The resulting control strategy adds only a small computational overhead, leading to quick visual feedback for resolutions allowing interactive simulation. We demonstrate the robustness and ease of use of our method on various examples in 2D and 3D.
A Pixel-Based Framework for Data-Driven Clothing
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Jin, Ning; Zhu, Yilin; Geng, Zhenglin; Fedkiw, Ron; Bender, Jan and Popa, Tiberiu
We propose a novel approach to learning cloth deformation as a function of body pose, recasting the graph-like triangle mesh data structure into image-based data in order to leverage popular and well-developed convolutional neural networks (CNNs) in a two-dimensional Euclidean domain. Then, a three-dimensional animation of clothing is equivalent to a sequence of twodimensional RGB images driven/choreographed by time dependent joint angles. In order to reduce nonlinearity demands on the neural network, we utilize procedural skinning of the body surface to capture much of the rotation/deformation so that the RGB images only contain textures of displacement offsets from skin to clothing. Notably, we illustrate that our approach does not require accurate unclothed body shapes or robust skinning techniques. Additionally, we discuss how standard image based techniques such as image partitioning for higher resolution can readily be incorporated into our framework.
Primal/Dual Descent Methods for Dynamics
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Macklin, Miles; Erleben, Kenny; Müller, Matthias; Chentanez, Nuttapong; Jeschke, Stefan; Kim, Tae-Yong; Bender, Jan and Popa, Tiberiu
We examine the relationship between primal, or force-based, and dual, or constraint-based formulations of dynamics. Variational frameworks such as Projective Dynamics have proved popular for deformable simulation, however they have not been adopted for contact-rich scenarios such as rigid body simulation. We propose a new preconditioned frictional contact solver that is compatible with existing primal optimization methods, and competitive with complementarity-based approaches. Our relaxed primal model generates improved contact force distributions when compared to dual methods, and has the advantage of being differentiable, making it well-suited for trajectory optimization. We derive both primal and dual methods from a common variational point of view, and present a comprehensive numerical analysis of both methods with respect to conditioning. We demonstrate our method on scenarios including rigid body contact, deformable simulation, and robotic manipulation.
Probabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Model
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Ghorbani, Saeed; Wloka, Calden; Etemad, Ali; Brubaker, Marcus A.; Troje, Nikolaus F.; Bender, Jan and Popa, Tiberiu
We present a probabilistic framework to generate character animations based on weak control signals, such that the synthesized motions are realistic while retaining the stochastic nature of human movement. The proposed architecture, which is designed as a hierarchical recurrent model, maps each sub-sequence of motions into a stochastic latent code using a variational autoencoder extended over the temporal domain. We also propose an objective function which respects the impact of each joint on the pose and compares the joint angles based on angular distance. We use two novel quantitative protocols and human qualitative assessment to demonstrate the ability of our model to generate convincing and diverse periodic and non-periodic motion sequences without the need for strong control signals.
Statistics-based Motion Synthesis for Social Conversations
(The Eurographics Association and John Wiley & Sons Ltd., 2020) Yang, Yanzhe; Yang, Jimei; Hodgins, Jessica; Bender, Jan and Popa, Tiberiu
Plausible conversations among characters are required to generate the ambiance of social settings such as a restaurant, hotel lobby, or cocktail party. In this paper, we propose a motion synthesis technique that can rapidly generate animated motion for characters engaged in two-party conversations. Our system synthesizes gestures and other body motions for dyadic conversations that synchronize with novel input audio clips. Human conversations feature many different forms of coordination and synchronization. For example, speakers use hand gestures to emphasize important points, and listeners often nod in agreement or acknowledgment. To achieve the desired degree of realism, our method first constructs a motion graph that preserves the statistics of a database of recorded conversations performed by a pair of actors. This graph is then used to search for a motion sequence that respects three forms of audio-motion coordination in human conversations: coordination to phonemic clause, listener response, and partner's hesitation pause. We assess the quality of the generated animations through a user study that compares them to the originally recorded motion and evaluate the effects of each type of audio-motion coordination via ablation studies.

Browse

Browsing 39-Issue 8 by Subject "Computing methodologies"

Results Per Page

Sort Options