SCA 2023: Eurographics/SIGGRAPH Symposium on Computer Animation
Permanent URI for this collection
Browse
Browsing SCA 2023: Eurographics/SIGGRAPH Symposium on Computer Animation by Issue Date
Now showing 1 - 20 of 22
Results Per Page
Sort Options
Item Proceedings Information(ACM, 2023) Wang, Huamin; Ye, Yuting; Victor ZordanItem Adaptive Rigidification of Discrete Shells(ACM Association for Computing Machinery, 2023) Mercier-Aubin, Alexandre; Kry, Paul G.; Wang, Huamin; Ye, Yuting; Victor ZordanWe present a method to improve the computation time of thin shell simulations by using adaptive rigidification to reduce the number of degrees of freedom. Our method uses a discretization independent metric for bending rates, and we derive a membrane strain rate to curvature rate equivalence that permits the use of a common threshold. To improve accuracy, we enhance the elastification oracle by considering both membrane and bending deformation to determine when to rigidify or elastify. Furthermore, we explore different approaches that are compatible with the previous work on adaptive rigidifcation and enhance the accuracy of the elastification on new contacts without increasing the computational overhead. Additionally, we propose a scaling approach that reduces the conditioning issues that arise from mixing rigid and elastic bodies in the same model.Item ACT2G: Attention-based Contrastive Learning for Text-to-Gesture Generation(ACM Association for Computing Machinery, 2023) Teshima, Hitoshi; Wake, Naoki; Thomas, Diego; Nakashima, Yuta; Kawasaki, Hiroshi; Ikeuchi, Katsushi; Wang, Huamin; Ye, Yuting; Victor ZordanRecent increase of remote-work, online meeting and tele-operation task makes people find that gesture for avatars and communication robots is more important than we have thought. It is one of the key factors to achieve smooth and natural communication between humans and AI systems and has been intensively researched. Current gesture generation methods are mostly based on deep neural network using text, audio and other information as the input, however, they generate gestures mainly based on audio, which is called a beat gesture. Although the ratio of the beat gesture is more than 70% of actual human gestures, content based gestures sometimes play an important role to make avatars more realistic and human-like. In this paper, we propose a attention-based contrastive learning for text-to-gesture (ACT2G), where generated gestures represent content of the text by estimating attention weight for each word from the input text. In the method, since text and gesture features calculated by the attention weight are mapped to the same latent space by contrastive learning, once text is given as input, the network outputs a feature vector which can be used to generate gestures related to the content. User study confirmed that the gestures generated by ACT2G were better than existing methods. In addition, it was demonstrated that wide variation of gestures were generated from the same text by changing attention weights by creators.Item NeuroDog: Quadruped Embodiment using Neural Networks(ACM Association for Computing Machinery, 2023) Egan, Dónal; Cosker, Darren; McDonnell, Rachel; Wang, Huamin; Ye, Yuting; Victor ZordanVirtual reality (VR) allows us to immerse ourselves in alternative worlds in which we can embody avatars to take on new identities. Usually, these avatars are humanoid or possess very strong anthropomorphic qualities. Allowing users of VR to embody non-humanoid virtual characters or animals presents additional challenges. Extreme morphological differences and the complexities of different characters’ motions can make the construction of a real-time mapping between input human motion and target character motion a difficult challenge. Previous animal embodiment work has focused on direct mapping of human motion to the target animal via inverse kinematics. This can lead to the target animal moving in a way which is inappropriate or unnatural for the animal type. We present a novel real-time method, incorporating two neural networks, for mapping human motion to realistic quadruped motion. Crucially, the output quadruped motions are realistic, while also being faithful to the input user motions.We incorporate our mapping into a VR embodiment system in which users can embody a virtual quadruped from a first person perspective. Further, we evaluate our system via a perceptual experiment in which we investigate the quality of the synthesised motion, the system’s response to user input and the sense of embodiment experienced by users. The main findings of the study are that the system responds as well as traditional embodiment systems to user input, produces higher quality motion and users experience a higher sense of body ownership when compared to a baseline method in which the human to quadruped motion mapping relies solely on inverse kinematics. Finally, our embodiment system relies solely on consumer-grade hardware, thus making it appropriate for use in applications such as VR gaming or VR social platforms.Item DiffXPBD : Differentiable Position-Based Simulation of Compliant Constraint Dynamics(ACM Association for Computing Machinery, 2023) Stuyck, Tuur; Chen, Hsiao-Yu; Wang, Huamin; Ye, Yuting; Victor ZordanWe present DiffXPBD, a novel and efficient analytical formulation for the differentiable position-based simulation of compliant constrained dynamics (XPBD). Our proposed method allows computation of gradients of numerous parameters with respect to a goal function simultaneously leveraging a performant simulation model. The method is efficient, thus enabling differentiable simulations of high resolution geometries and degrees of freedom (DoFs). Collisions are naturally included in the framework. Our differentiable model allows a user to easily add additional optimization variables. Every control variable gradient requires the computation of only a few partial derivatives which can be computed using automatic differentiation code. We demonstrate the efficacy of the method with examples such as elastic cloth and volumetric material parameter estimation, initial value optimization, optimizing for underlying body shape and pose by only observing the clothing, and optimizing a time-varying external force sequence to match sparse keyframe shapes at specific times. Our approach demonstrates excellent efficiency and we demonstrate this on high resolution meshes with optimizations involving over 26 million degrees of freedom. Making an existing solver differentiable requires only a few modifications and the model is compatible with both modern CPU and GPU multi-core hardware.Item A Multilevel Active-Set Preconditioner for Box-Constrained Pressure Poisson Solvers(ACM Association for Computing Machinery, 2023) Takahashi, Tetsuya; Batty, Christopher; Wang, Huamin; Ye, Yuting; Victor ZordanEfficiently solving large-scale box-constrained convex quadratic programs (QPs) is an important computational challenge in physical simulation.We propose a new multilevel preconditioning scheme based on the active-set method and combine it with modified proportioning with reduced gradient projections (MPRGP) to efficiently solve such QPs arising from pressure Poisson equations with non-negative pressure constraints in fluid animation. Our method employs a purely algebraic multigrid method to ensure the solvability of the coarser level systems and to merge only algebraically-connected components, thereby avoiding performance degradation of the preconditioner. We present a filtering scheme to efficiently apply our multilevel preconditioning only to unconstrained subsystems of the pressure Poisson system while reusing the hierarchy constructed per simulation step. We demonstrate the effectiveness of our method over previous approaches in various examples.Item A Generalized Constitutive Model for Versatile MPM Simulation and Inverse Learning with Differentiable Physics(ACM Association for Computing Machinery, 2023) Su, Haozhe; Li, Xuan; Xue, Tao; Jiang, Chenfanfu; Aanjaneya, Mridul; Wang, Huamin; Ye, Yuting; Victor ZordanWe present a generalized constitutive model for versatile physics simulation of inviscid fluids, Newtonian viscosity, hyperelasticity, viscoplasticity, elastoplasticity, and other physical effects that arise due to a mixture of these behaviors. The key ideas behind our formulation are the design of a generalized Kirchhoff stress tensor that can describe hyperelasticity, Newtonian viscosity and inviscid fluids, and the use of pre-projection and post-correction rules for simulating material behaviors that involve plasticity, including elastoplasticity and viscoplasticity.We show how our generalized Kirchhoff stress tensor can be coupled together into a generalized constitutive model that allows the simulation of diverse material behaviors by only changing parameter values. We present several side-by-side comparisons with physics simulations for specific constitutive models to show that our generalized model produces visually similar results. More notably, our formulation allows for inverse learning of unknown material properties directly from data using differentiable physics simulations. We present several 3D simulations to highlight the robustness of our method, even with multiple different materials. To the best of our knowledge, our approach is the first to recover the knowledge of unknown material properties without making explicit assumptions about the data.Item Two-Way Coupling of Skinning Transformations and Position Based Dynamics(ACM Association for Computing Machinery, 2023) Wu, Yuhan; Umetani, Nobuyuki; Wang, Huamin; Ye, Yuting; Victor ZordanSkinning transformations enable digital characters to be animated with minimal user input. Physics simulations can improve the detailed dynamic movement of an animated character; however, such details are typically added in the post-processing stage after the overall animation is specified.We propose a novel interactive framework that unifies skinning transformations and kinematic simulations using position-based dynamics (PBD). Our framework allows an arbitrarily skinned character to be partially manipulated by the user, and a kinematic physics solver automatically complements the behavior of the entire character. This is achieved by introducing new steps into the PBD algorithm: (i) lightweight optimization to identify the skinning transformations, which is similar to inverse kinematics, and (ii) a position-based constraint to restrict the PBD solver to the complementary subspace of the skinning deformation. Our method combines the best of the two methods: the controllability and shape preservation of the skinning transformation, and the efficiency, simplicity, and unconditional stability of the PBD solver. Our interface allows novices to create vibrant animations without tedious editing.Item Too Stiff, Too Strong, Too Smart: Evaluating Fundamental Problems with Motion Control Policies(ACM Association for Computing Machinery, 2023) Xie, Kaixiang; Xu, Pei; Andrews, Sheldon; Zordan, Victor B.; Kry, Paul G.; Wang, Huamin; Ye, Yuting; Victor ZordanDeep reinforcement learning (DRL) methods have demonstrated impressive results for skilled motion synthesis of physically based characters, and while these methods perform well in terms of tracking reference motions or achieving complex tasks, several concerns arise when evaluating the naturalness of the motion. In this paper, we conduct a preliminary study of specific quantitative metrics for measuring the naturalness of motion produced by DRL control policies beyond their visual appearance. Namely, we propose to study the stiffness of the control policy, in anticipation that it will influence how the character behaves in the presence of external perturbation. Second, we establish two baselines for strength that allow evaluating the use of joint torques in comparison to human performance. Third, we propose the study of variability to reveal the unnatural precision of control policies and how they compare to real human motion. In sum, we aim to establish repeatable measures to assess the naturalness of control policies produced by DRL methods, and we present a set of comparisons from state-of-the-art systems. Finally, we propose simple modifications to improve realism on these axes.Item A Unified Analysis of Penalty-Based Collision Energies(ACM Association for Computing Machinery, 2023) Shi, Alvin; Kim, Theodore; Wang, Huamin; Ye, Yuting; Victor ZordanWe analyze a wide class of penalty energies used for contact response through the lens of a reduced frame. Applying our analysis to both spring-based and barrier-based energies, we show that we can obtain closedform, analytic eigensystems that can be used to guarantee positive semidefiniteness in implicit solvers. Our approach is both faster than direct numerical methods, and more robust than approximate methods such as Gauss-Newton. Over the course of our analysis, we investigate physical interpretations for two separate notions of length. Finally, we showcase the stability of our analysis on challenging strand, cloth, and volume scenarios with large timesteps on the order of 1/40 s.Item Physics-based Motion Retargeting from Sparse Inputs(ACM Association for Computing Machinery, 2023) Reda, Daniele; Won, Jungdam; Ye, Yuting; Panne, Michiel van de; Winkler, Alexander; Wang, Huamin; Ye, Yuting; Victor ZordanAvatars are important to create interactive and immersive experiences in virtual worlds. One challenge in animating these characters to mimic a user’s motion is that commercial AR/VR products consist only of a headset and controllers, providing very limited sensor data of the user’s pose. Another challenge is that an avatar might have a different skeleton structure than a human and the mapping between them is unclear. In this work we address both of these challenges. We introduce a method to retarget motions in real-time from sparse human sensor data to characters of various morphologies. Our method uses reinforcement learning to train a policy to control characters in a physics simulator. We only require human motion capture data for training, without relying on artist-generated animations for each avatar. This allows us to use large motion capture datasets to train general policies that can track unseen users from real and sparse data in real-time.We demonstrate the feasibility of our approach on three characters with different skeleton structure: a dinosaur, a mouse-like creature and a human.We show that the avatar poses often match the user surprisingly well, despite having no sensor information of the lower body available. We discuss and ablate the important components in our framework, specifically the kinematic retargeting step, the imitation, contact and action reward as well as our asymmetric actor-critic observations. We further explore the robustness of our method in a variety of settings including unbalancing, dancing and sports motions.Item Motion In-Betweening with Phase Manifolds(ACM Association for Computing Machinery, 2023) Starke, Paul; Starke, Sebastian; Komura, Taku; Steinicke, Frank; Wang, Huamin; Ye, Yuting; Victor ZordanThis paper introduces a novel data-driven motion in-betweening system to reach target poses of characters by making use of phases variables learned by a Periodic Autoencoder. Our approach utilizes a mixture-of-experts neural network model, in which the phases cluster movements in both space and time with different expert weights. Each generated set of weights then produces a sequence of poses in an autoregressive manner between the current and target state of the character. In addition, to satisfy poses which are manually modified by the animators or where certain end effectors serve as constraints to be reached by the animation, a learned bi-directional control scheme is implemented to satisfy such constraints. The results demonstrate that using phases for motion in-betweening tasks sharpen the interpolated movements, and furthermore stabilizes the learning process. Moreover, using phases for motion in-betweening tasks can also synthesize more challenging movements beyond locomotion behaviors. Additionally, style control is enabled between given target keyframes. Our proposed framework can compete with popular state-of-the-art methods for motion in-betweening in terms of motion quality and generalization, especially in the existence of long transition durations. Our framework contributes to faster prototyping workflows for creating animated character sequences, which is of enormous interest for the game and film industry.Item HDHumans: A Hybrid Approach for High-fidelity Digital Humans(ACM Association for Computing Machinery, 2023) Habermann, Marc; Liu, Lingjie; Xu, Weipeng; Pons-Moll, Gerard; Zollhoefer, Michael; Theobalt, Christian; Wang, Huamin; Ye, Yuting; Victor ZordanPhoto-real digital human avatars are of enormous importance in graphics, as they enable immersive communication over the globe, improve gaming and entertainment experiences, and can be particularly beneficial for AR and VR settings. However, current avatar generation approaches either fall short in high-fidelity novel view synthesis, generalization to novel motions, reproduction of loose clothing, or they cannot render characters at the high resolution offered by modern displays. To this end, we propose HDHumans, which is the first method for HD human character synthesis that jointly produces an accurate and temporally coherent 3D deforming surface and highly photo-realistic images of arbitrary novel views and of motions not seen at training time. At the technical core, our method tightly integrates a classical deforming character template with neural radiance fields (NeRF). Our method is carefully designed to achieve a synergy between classical surface deformation and a NeRF. First, the template guides the NeRF, which allows synthesizing novel views of a highly dynamic and articulated character and even enables the synthesis of novel motions. Second, we also leverage the dense pointclouds resulting from the NeRF to further improve the deforming surface via 3D-to-3D supervision. We outperform the state of the art quantitatively and qualitatively in terms of synthesis quality and resolution, as well as the quality of 3D surface reconstruction.Item Physical Cyclic Animations(ACM Association for Computing Machinery, 2023) Jia, Shiyang; Wang, Stephanie; Li, Tzu-Mao; Chern, Albert; Wang, Huamin; Ye, Yuting; Victor ZordanWe address the problem of synthesizing physical animations that can loop seamlessly. We formulate a variational approach by deriving a physical law in a periodic time domain. The trajectory of the animation is represented as a parametric closed curve, and the physical law corresponds to minimizing the bending energy of the curve. Compared to traditional keyframe animation approaches, our formulation is constraint-free, which allows us to apply a standard Gauss–Newton solver. We further propose a fast projection method to efficiently generate an initial guess close to the desired animation. Our method can handle a variety of physical cyclic animations, including clothes, soft bodies with collisions, and N-body systems.Item A Linear and Angular Momentum Conserving Hybrid Particle/Grid Iteration for Volumetric Elastic Contact(ACM Association for Computing Machinery, 2023) Razon, Alan Marquez; Chen, Yizhou; Yushan, Han; Gagniere, Steven; Tupek, Michael; Teran, Joseph; Wang, Huamin; Ye, Yuting; Victor ZordanWe present a momentum conserving hybrid particle/grid iteration for resolving volumetric elastic collision. Our hybrid method uses implicit time stepping with a Lagrangian finite element discretization of the volumetric elastic material together with impulse-based collision-correcting momentum updates designed to exactly conserve linear and angular momentum. We use a two-step process for collisions: first we use a novel gridbased approach that leverages the favorable collision resolution properties of Particle-In-Cell (PIC) techniques, then we finalize with a classical collision impulse strategy utilizing continuous collision detection. Our PIC approach uses Affine-Particle-In-Cell momentum transfers as collision preventing impulses together with novel perfectly momentum conserving boundary resampling and downsampling operators that prevent artifacts in portions of the boundary where the grid resolution is of disparate resolution. We combine this with a momentum conserving augury iteration to remove numerical cohesion and model sliding friction. Our collision strategy has the same continuous collision detection as traditional approaches, however our hybrid particle/grid iteration drastically reduces the number of iterations required. Lastly, we develop a novel symmetric positive semi-definite Rayleigh damping model that increases the convexity of the nonlinear systems associated with implicit time stepping. We demonstrate the robustness and efficiency of our approach in a number of collision intensive examples.Item A comparison of linear consistent correction methods for first-order SPH derivatives(ACM Association for Computing Machinery, 2023) Westhofen, Lukas; Jeske, Stefan; Bender, Jan; Wang, Huamin; Ye, Yuting; Victor ZordanAwell-known issue with the widely used Smoothed Particle Hydrodynamics (SPH) method is the neighborhood deficiency. Near the surface, the SPH interpolant fails to accurately capture the underlying fields due to a lack of neighboring particles. These errors may introduce ghost forces or other visual artifacts into the simulation. In this work we investigate three different popular methods to correct the first-order spatial derivative SPH operators up to linear accuracy, namely the Kernel Gradient Correction (KGC), Moving Least Squares (MLS) and Reproducing Kernel Particle Method (RKPM). We provide a thorough, theoretical comparison in which we remark strong resemblance between the aforementioned methods. We support this by an analysis using synthetic test scenarios. Additionally, we apply the correction methods in simulations with boundary handling, viscosity, surface tension, vorticity and elastic solids to showcase the reduction or elimination of common numerical artifacts like ghost forces. Lastly, we show that incorporating the correction algorithms in a state-of-the-art SPH solver only incurs a negligible reduction in computational performance.Item Micropolar Elasticity in Physically-Based Animation(ACM Association for Computing Machinery, 2023) Löschner, Fabian; Fernández-Fernández, José Antonio; Jeske, Stefan Rhys; Longva, Andreas; Bender, Jan; Wang, Huamin; Ye, Yuting; Victor ZordanWe explore micropolar materials for the simulation of volumetric deformable solids. In graphics, micropolar models have only been used in the form of one-dimensional Cosserat rods, where a rotating frame is attached to each material point on the one-dimensional centerline. By carrying this idea over to volumetric solids, every material point is associated with a microrotation, an independent degree of freedom that can be coupled to the displacement through a material’s strain energy density. The additional degrees of freedom give us more control over bending and torsion modes of a material. We propose a new orthotropic micropolar curvature energy that allows us to make materials stiff to bending in specific directions. For the simulation of dynamic micropolar deformables we propose a novel incremental potential formulation with a consistent FEM discretization that is well suited for the use in physically-based animation. This allows us to easily couple micropolar deformables with dynamic collisions through a contact model inspired from the Incremental Potential Contact (IPC) approach. For the spatial discretization with FEM we discuss the challenges related to the rotational degrees of freedom and propose a scheme based on the interpolation of angular velocities followed by quaternion time integration at the quadrature points. In our evaluation we validate the consistency and accuracy of our discretization approach and demonstrate several compelling use cases for micropolar materials. This includes explicit control over bending and torsion stiffness, deformation through prescription of a volumetric curvature field and robust interaction of micropolar deformables with dynamic collisions.Item An Eigenanalysis of Angle-Based Deformation Energies(ACM Association for Computing Machinery, 2023) Wu, Haomiao; Kim, Theodore; Wang, Huamin; Ye, Yuting; Victor ZordanAngle-based energies appear in numerous physics-based simulation models, including thin-shell bending and isotropic elastic strands. We present a generic analysis of these energies that allows us to analytically filter the negative eigenvalues of the second derivative (Hessian), which is critical for stable, implicit time integration. While these energies are usually formulated in terms of angles and positions, we propose an abstract edge stencil that succinctly parameterizes the edge deformation, and allows us to derive generic, closed-form analytical expressions for the energy eigensystems. The resultant eigenvectors have straightforward geometric interpretations. We demonstrate that our method is readily applicable to a variety of 2D and 3D angle-based elastic energies, including both cloth and strands, and is up to 7× faster than numerical eigendecomposition.Item MAAIP: Multi-Agent Adversarial Interaction Priors for imitation from fighting demonstrations for physics-based characters(ACM Association for Computing Machinery, 2023) Younes, Mohamed; Kijak, Ewa; Kulpa, Richard; Malinowski, Simon; Multon, Franck; Wang, Huamin; Ye, Yuting; Victor ZordanSimulating realistic interaction and motions for physics-based characters is of great interest for interactive applications, and automatic secondary character animation in the movie and video game industries. Recent works in reinforcement learning have proposed impressive results for single character simulation, especially the ones that use imitation learning based techniques. However, imitating multiple characters interactions and motions requires to also model their interactions. In this paper, we propose a novel Multi-Agent Generative Adversarial Imitation Learning based approach that generalizes the idea of motion imitation for one character to deal with both the interaction and the motions of the multiple physics-based characters. Two unstructured datasets are given as inputs: 1) a single-actor dataset containing motions of a single actor performing a set of motions linked to a specific application, and 2) an interaction dataset containing a few examples of interactions between multiple actors. Based on these datasets, our system trains control policies allowing each character to imitate the interactive skills associated with each actor, while preserving the intrinsic style. This approach has been tested on two different fighting styles, boxing and full-body martial art, to demonstrate the ability of the method to imitate different styles.Item Towards Realtime: A Hybrid Physics-based Method for Hair Animation on GPU(ACM Association for Computing Machinery, 2023) Huang, Li; Yang, Fan; Wie, Chendi; Chen, Yu Ju (Edwin); Yuan, Chun; Gao, Ming; Wang, Huamin; Ye, Yuting; Victor ZordanThis paper introduces a hair simulator optimized for real-time applications, including console and cloud gaming, avatar live-streaming, and metaverse environments. We view the collisions between strands as a mechanism to preserve the overall volume of the hair and adopt explicit Material Point Method (MPM) to resolve the strand-strand collision. For simulating single-strand behavior, a semi-implicit Discrete Elastic Rods (DER) model is used. We build upon a highly efficient GPU MPM framework recently presented by Fei et al. [2021b] and propose several schemes to largely improve the performance of building and solving the semi-implicit DER systems on GPU. We demonstrate the efficiency of our pipeline by a few practical scenes that achieve up to 260 frames-per-second (FPS) with more than two thousand simulated strands on Nvidia GeForce RTX 3080.