Positioning clothing parts ($\mathcal {S}$Ss) such as sleeves and collars has been in the realm of manual task that had to be done meticulously in order to prevent unnecessary tanglements during the simulation. This article proposes an optimization-based method to computerize the above $\mathcal {S}$S-positioning task. For that, we embed each $\mathcal {S}$S to an abstracting cylinder $\mathcal {C}$C such that $\mathcal {S}$S-positioning can be done by adjusting only 3$\sim$∼4 DOFs (e.g., translating/rotating $\mathcal {C}$C or adjusting its radius) instead of per-vertex-full-DOFs. Then, we formulate an objective function $E$E by scoring undesirableness of $\mathcal {S}$S's position (e.g., $\mathcal {S}$S penetrating the body, $\mathcal {S}$S making cloth-to-cloth intersection). In organizing $E$E into the loop of the Newton's method, the main challenge was to calculate the symbolic gradient and hessian, for which this article makes several novel contributions. The resultant $\mathcal {S}$S-positioning method works quite successfully; $\mathcal {S}^*$S*s (the output of the $\mathcal {S}$S-positioning method) are tanglement-free thus running the simulator to that configuration produces acceptable draping quickly; Experiments show that, in obtaining acceptable draping, the proposed method produces about $\times 9.7$×9.7 speed up compared to when not using it.

This article proposes a new discrete collision handling method (DCH method) that can be used for resolving tanglements in clothing simulation, based on the existing continuous collision handling methods (CCH methods). The proposed method performs intersection analysis of the clothing mesh at every time step, and stores the result in the form of coloring the vertices, edges, and triangles. Referring to the coloring, the method resolves the tanglements in the out-to-in manner by applying the proposed operations, the triangle shrinkage and vertex pull, to the triangles and vertices around the intersection path. We take note of the CCH methods that use some small tolerance value to defend the round-off errors for the purpose of preventing false negatives. This work gives a second thought to that tolerance value, and proposes a new DCH method which uses the tolerance value for the resolution purpose. Under certain conditions, the method turns out to guarantee resolution of the tanglements in a finite number of time steps.

Face recognition now requires a large number of labelled masked face images in the era of this unprecedented COVID19 pandemic. Unfortunately, the rapid spread of the virus has left us little time to prepare for such dataset in the wild. To circumvent this issue, we present a 3D model-based approach called WearMask3D for augmenting face images of various poses to the masked face counterparts. Our method proceeds by first fitting a 3D morphable model on the input image, second overlaying the mask surface onto the face model and warping the respective mask texture, and last projecting the 3D mask back to 2D. The mask texture is adapted based on the brightness and resolution of the input image. By working in 3D, our method can produce more natural masked faces of diverse poses from a single mask texture. To compare precisely between different augmentation approaches, we have constructed a dataset comprising masked and unmasked faces with labels called MFW-mini. Experimental results demonstrate WearMask3D1produces more realistic masked faces, and utilizing these images for training leads to state-of-the-art recognition accuracy for masked faces.

This paper proposes a new method that can be used when virtual ensembles need to be put on to a 3D avatar. We assume that input to the virtual fitting system is a number of garments draped on a target avatar. Then, the problem is to account for the interference between the garments and produce the scene in which the constituent garments are worn in an ensemble. For that, we propose a technique to stratify the garments such that they do not intersect in any region, thus the conventional simulators can start from a workable initial configuration. Then, we introduce the regional simulation omission, which can generate try-on of ensembles in a significantly reduced amount of time. Experiments show that, in the robustness, processing speed, and flexibility, the proposed method is strikingly better than the conventional approach.

Abstract In this pa Per , we introduce so‐called the bSX method as a new way to utilize the Kubelka‐Munk (K‐M) model. Assuming the material is completely diffusive, the K‐M model gives the reflectance and transmittance of the material from the observation of the material applied on a backing, where the observation includes the thickness of the material application. By rearranging the original K‐M equation, we propose that the reflectance and transmittance can be calculated without knowing the thickness. This is a practically useful contribution. Based on the above finding, we develop the bSX method which can (1) capture the material specific parameters from the two photos – taken before and after the material application, and (2) reproduce its effect on a novel backing. We ex Per imented the proposed method in various cases related to virtual cosmetic try‐on, which include (1) capture from a single color backing, (2) capture from human skin backing, (3) reproduction of varying thickness effect, (4) reproduction of multi‐layer cosmetic application effect, (5) applying the proposed method to makeup transfer. Compared to previous image‐based makeup transfer methods, the bSX method reproduces the feel of the cosmetics more accurately.

Abstract This paper presents a new method which can create the virtual garment from a single photograph of a real garment put on to the mannequin. In solving this problem, we obtain the insight from the pattern drafting theory in the clothing field. We abstract the drafting process into a computer module, which takes the garment type and primary body sizes then produces the draft as the output. Then the problem is reduced to find out the garment type and primary body sizes. We find that information by analyzing the silhouette of the garment with respect to the mannequin. The method works robustly and produces practically usable virtual clothes that can be used for the graphical coordination. Copyright © 2015 John Wiley & Sons, Ltd.

Abstract We present a new framework to simulate moving interfaces in viscous incompressible two phase flows. The goal is to achieve both conservation of the fluid volume and a detailed reconstruction of the fluid surface. To these ends, we incorporate sub‐grid refinement of the level set with the volume‐of‐fluid method. In the context of this refined level set grid we propose the algorithms needed for the coupling of the level set and the volume‐of‐fluid, which include techniques for computing volume, redistancing the level set, and handling surface tension. We report the experimental results produced with the proposed method via simulations of the two phase fluid phenomena such as air‐cushioning and deforming large bubbles.

Abstract We present a new technique which can handle both point and sliding constraints in the multigrid (MG) framework. Although the MG method can theoretically perform as fast as O(N), the development of a clothing simulator based on the MG method calls for solving an important technical challenge: handling the constraints. Resolving constrains has been difficult in MG because there has been no clear way to transfer the constraints existing in the finest level mesh to the coarser level meshes. This paper presents a new formulation based on soft constraints, which can coarsen the constraints defined in the finest level to the coarser levels. Experiments are performed which show that the proposed method can solve the linear system up to 4–9 times faster in comparison with the modified preconditioned conjugate gradient method (MPCG) without quality degradation. The proposed method is easy to implement and can be straightforwardly applied to existing clothing simulators which are based on implicit time integration.

ABSTRACT This paper presents a novel framework for garment grading. In CG, an extensive amount of study has been carried out to clothe human characters, but little attention has been taken to the grading problem itself. For the development of a grading technique, we obtained the insight from the process of drawing the patternmaking draft (sloper) in the clothing field. Noting that the draft can be completely determined by supplying the primary body sizes, we abstract the draft construction process as a computer procedure, which we call the parametrized draft. With the parametrized draft, we develop a grading method based on the draft‐space warping, which takes three steps: (i) draft‐space encoding, (ii) target draft construction, then (iii) draft‐space decoding. The proposed grading method can be performed instantly for any given body without calling for the user's intervention. With experimental results, we show that the new grading framework can bring an improvement to garment grading. Copyright © 2013 John Wiley & Sons, Ltd.

The explosive or volcanic scenes in motion pictures involve complex turbulent flow as its temperature and density vary in space. To simulate this turbulent flow of an inhomogeneous fluid, we propose a simple and efficient framework. Instead of explicitly computing the complex motion of this fluid dynamical instability, we first approximate the average motion of the fluid. Then, the high-resolution dynamics is computed using our new extended version of the vortex particle method with baroclinity. This baroclinity term makes turbulent effects by generating new vortex particles according to temperature/density distributions. Using our method, we efficiently simulated a complex scene with varying density and temperature.

This paper introduces a fully-Eulerian interface tracking framework that preserves the fine details of liquids. Unlike existing Eulerian methods, the proposed framework shows good mass conservation even though it does not employ conventional Lagrangian elements. In addition, it handles complex merging and splitting of interfaces robustly due to the implicit representation. To model the interface more accurately, a high order polynomial reconstruction of the signed distance function is utilized based on a number of sub-grid quadrature points. By combining this accurate polynomial representation with a high-order re-initialization method, the proposed framework preserves the detailed structures of the interface. Moreover, the method is simple to implement, unconditionally stable, and is suitable for parallel computing environments.

In this paper, we propose a simple and efficient framework for simulating dispersed bubble flow. Instead of modeling the complex hydrodynamics of numerous small bubbles explicitly, our method approximates the average motion of these bubbles using a continuum multiphase solver. Then, the subgrid interactions among bubbles are computed using our new stochastic solver. Using the proposed scheme, we can efficiently simulate complex scenes with millions of bubbles.

This paper presents a novel framework for simulating the stretching and wiggling of liquids. We demonstrate that complex phase-interface dynamics can be effectively simulated by introducing the Eulerian vortex sheet method, which focuses on the vorticity at the interface (rather than the whole domain). We extend this model to provide user control for the production of visual effects. Then, the generated fluid flow creates complex surface details, such as thin and wiggling fluid sheets. To capture such high-frequency features efficiently, this work employs a denser grid for surface tracking in addition to the (coarser) simulation grid. In this context, the paper proposes a filter, called the liquid-biased filter, which is able to downsample the surface in the high-resolution grid into the coarse grid without unrealistic volume loss resulting from aliasing error. The proposed method, which runs on a single PC, realistically reproduces complex fluid scenes.

Abstract In this paper, we propose a new constrained interpolation profile (CIP) method that is stable and accurate but requires less amount of computation compared to existing CIP‐based solvers. CIP is a high‐order fluid advection solver that can reproduce rich details of fluids. It has third‐order accuracy but its computation is performed over a compact stencil. These advantageous features of CIP are, however, diluted by the following two shortcomings: (1) CIP contains a defect in the utilization of the grid data, which makes the method suitable only for simulations with a tight CFL restriction; and (2) CIP does not guarantee unconditional stability. There have been several attempts to fix these problems in CIP, but they have been only partially successful. The solutions that fixed both problems ended up introducing other undesirable features, namely increased computation time and/or reduced accuracy. This paper proposes a novel modification of the original CIP method that fixes all of the above problems without increasing the computational load or reducing the accuracy. Both quantitative and visual experiments were performed to test the performance of the new CIP in comparison to existing fluid solvers. The results show that the proposed method brings significant improvements in both accuracy and speed.

Abstract This paper proposes a real‐time simulation technique for thin shells undergoing large deformation. Shells are thin objects such as leaves and papers that can be abstracted as 2D structures. Development of a satisfactory physical model that runs in real‐time but produces visually convincing animation of thin shells has been remaining a challenge in computer graphics. Rather than resorting to shell theory which involves the most complex formulations in continuum mechanics, we adopt the energy functions from the discrete shells proposed by Grinspun et al. [ GHDS03 ]. For real‐time integration of the governing equation, we develop a modal warping technique for shells. This new simulation framework results from making extensions to the original modal warping technique [ CK05 ] which was developed for the simulation of 3D solids. We report experimental results, which show that the proposed method runs in real‐time even for large meshes, and that it can simulate large bending and/or twisting deformations with acceptable realism.

Abstract This paper proposes a new technique for generating three‐dimensional speech animation. The proposed technique takes advantage of both data‐driven and machine learning approaches. It seeks to utilize the most relevant part of the captured utterances for the synthesis of input phoneme sequences. If highly relevant data are missing or lacking, then it utilizes less relevant (but more abundant) data and relies more heavily on machine learning for the lip‐synch generation. This hybrid approach produces results that are more faithful to real data than conventional machine learning approaches, while being better able to handle incompleteness or redundancy in the database than conventional data‐driven approaches. Experimental results, obtained by applying the proposed technique to the utterance of various words and phrases, show that (1) the proposed technique generates lip‐synchs of different qualities depending on the availability of the data, and (2) the new technique produces more realistic results than conventional machine learning approaches.

We present a new fluid simulation technique that significantly reduces the nonphysical dissipation of velocity. The proposed method is based on an apt use of particles and derivative information. We note that a major source of numerical dissipation in the conventional Navier-Stokes equations solver lies in the advection step. Hence, starting with the conventional grid-based simulator, when the details of fluid movements need to be simulated, we replace the advection part with a particle simulator. When swapping between the grid-based and particle-based simulators, the physical quantities such as the level set and velocity must be converted. For this purpose, we develop a novel dissipation-suppressing conversion procedure that utilizes the derivative information stored in the particles, as well as in the grid points. For the fluid regions where such details are not needed, the advection is simulated using an octree-based constrained interpolation profile (CIP) solver, which we develop in this work. Through several experiments, we show that the proposed technique can reproduce the detailed movements of high-Reynolds-number fluids such as droplets/bubbles, thin water sheets, and whirlpools. The increased accuracy in the advection, which forms the basis of the proposed technique, can also be used to produce better results in larger scale fluid simulations.

This article presents a physically-based technique for simulating water. This work is motivated by the "stable fluids" method, developed by Stam [1999], to handle gaseous fluids. We extend this technique to water, which calls for the development of methods for modeling multiphase fluids and suppressing dissipation. We construct a multiphase fluid formulation by combining the Navier--Stokes equations with the level set method. By adopting constrained interpolation profile (CIP)-based advection, we reduce the numerical dissipation and diffusion significantly. We further reduce the dissipation by converting potentially dissipative cells into droplets or bubbles that undergo Lagrangian motion. Due to the multiphase formulation, the proposed method properly simulates the interaction of water with surrounding air, instead of simulating water in a void space. Moreover, the introduction of the nondissipative technique means that, in contrast to previous methods, the simulated water does not unnecessarily lose mass, and its motion is not damped to an unphysical extent. Experiments showed that the proposed method is stable and runs fast. It is demonstrated that two-dimensional simulation runs in real-time.

This article presents a novel constraint-based motion editing technique. On the basis of animator-specified kinematic and dynamic constraints, the method converts a given captured or animated motion to a physically plausible motion. In contrast to previous methods using spacetime optimization, we cast the motion editing problem as a constrained state estimation problem, based on the per-frame Kalman filter framework. The method works as a filter that sequentially scans the input motion to produce a stream of output motion frames at a stable interactive rate. Animators can tune several filter parameters to adjust to different motions, turn the constraints on or off based on their contributions to the final result, or provide a rough sketch (kinematic hint) as an effective way of producing the desired motion. Experiments on various systems show that the technique processes the motions of a human with 54 degrees of freedom, at about 150 fps when only kinematic constraints are applied, and at about 10 fps when both kinematic and dynamic constraints are applied. Experiments on various types of motion show that the proposed method produces remarkably realistic animations.

This paper presents an interactive technique that produces static hairstyles by generating individual hair strands of the desired shape and color, subject to the presence of gravity and collisions. A variety of hairstyles can be generated by adjusting the wisp parameters, while the deformation is solved efficiently, accounting for the effects of gravity and collisions. Wisps are generated employing statistical approaches. As for hair deformation, we propose a method which is based on physical simulation concepts, but is simplified to efficiently solve the static shape of hair. On top of the statistical wisp model and the deformation solver, a constraint-based styler is proposed to model artificial features that oppose the natural flow of hair under gravity and hair elasticity, such as a hairpin. Our technique spans a wider range of human hairstyles than previously proposed methods and the styles generated by this technique are fairly realistic.

This paper proposes a real-time simulation technique for large deformations. Green's nonlinear strain tensor accurately models large deformations; however, time stepping of the resulting nonlinear system can be computationally expensive. Modal analysis based on a linear strain tensor has been shown to be suitable for real-time simulation, but is accurate only for moderately small deformations. In the present work, we identify the rotational component of an infinitesimal deformation and extend traditional linear modal analysis to track that component. We then develop a procedure to integrate the small rotations occurring at the nodal points. An interesting feature of our formulation is that it can implement both position and orientation constraints in a straightforward manner. These constraints can be used to interactively manipulate the shape of a deformable solid by dragging/twisting a set of nodes. Experiments show that the proposed technique runs in real-time, even for a complex model, and that it can simulate large bending and/or twisting deformations with acceptable realism.

This paper presents a new method for editing an existing motion to satisfy a set of user-specified constraints, and in doing so guaranteeing the kinematic and dynamic soundness of the transformed motion. We cast the motion editing problem as a constrained state estimation problem based on the per-frame Kalman filter framework. To handle various kinds of kinematic and dynamic constraints in a scalable fashion, we develop a new algorithm, called spacetime sweeping, which sweeps through the frames with two consecutive filters. The unscented Kalman (UK) filter estimates an optimal pose for the current frame that conforms to the given constraints, and feeds the result to the least-squares (LS) filter. Then, the LS filter resolves the inter-frame inconsistencies introduced by the UK filter due to the independent handling of the position, velocity and acceleration. The per-frame approach of the space-time sweeping provides a surprising performance gain. Thus editing of motion that involves dynamic constraints, such as dynamic balancing, can be done interactively.

We present a semi-implicit cloth simulation technique that is very stable yet also responsive. The stability of the technique allows the use of a large fixed time step when simulating all types of fabrics and character motions. The animations generated using this technique are strikingly realistic. Wrinkles form and disappear in a quite natural way, which is the feature that most distinguishes textile fabrics from other sheet materials. Significant improvements in both the stability and realism were made possible by overcoming the post-buckling instability as well as the numerical instability. The instability caused by buckling arises from a structural instability and therefore cannot be avoided by simply employing a semi-implicit method. Addition of a damping force may help to avoid instabilities; however, it can significantly degrade the realism of the cloth motion. The method presented here uses a particle-based physical model to handle the instability in the post-buckling response without introducing any fictitious damping.

We present a performance-driven facial animation system for analyzing captured expressions to find muscle actuation and synthesizing expressions with the actuation values. A significantly different approach of our work is that we let artists sculpt the initial draft of the actuation basis: the basic facial shapes corresponding to the isolated actuation of individual muscles, instead of calculating skin surface deformation entirely, relying on mathematical models such as finite element methods. We synthesize expressions by linear combinations of the basis elements, and analyze expressions by finding the weights for the combinations. Even though the hand-generated actuation basis represents the essence of the subject's characteristic expressions, it is not accurate enough to be used in the subsequent computational procedures. We also describe an iterative algorithm to increase the accuracy of the actuation basis. The experimental results suggest that our artist-in-the-loop method produces a more predictable and controllable outcome than pure mathematical models, and thus can be a quite useful tool in animation productions.

Abstract We describe a system to synthesize facial expressions by editing captured performances. For this purpose, we use the actuation of expression muscles to control facial expressions. We note that there have been numerous algorithms already developed for editing gross body motion. While the joint angle has direct effect on the configuration of the gross body, the muscle actuation has to go through a complicated mechanism to produce facial expressions. Therefore,we devote a significant part of this paper to establishing the relationship between muscle actuation and facial surface deformation. We model the skin surface using the finite element method to simulate the deformation caused by expression muscles. Then, we implement the inverse relationship, muscle actuation parameter estimation, to find the muscle actuation values from the trajectories of the markers on the performer's face. Once the forward and inverse relationships are established, retargeting or editing a performance becomes an easy job. We apply the original performance data to different facial models with equivalent muscle structures, to produce similar expressions. We also produce novel expressions by deforming the original data curves of muscle actuation to satisfy the key‐frame constraints imposed by animators.Copyright © 2001 John Wiley & Sons, Ltd.

In the field of geometry compression, two main compression targets exist. One is triangle connectivity data and the other is vertex position data. The authors propose a novel algorithm to compress the vertex data. A fundamentally different approach taken in the paper is to transform the vertex positions to the model space, a coordinate system formed by the three previously processed vertices. Once all the vertices are transformed, we found that the result shows a strong tendency to cluster around three points. We exploit such a tendency during the vector quantization steps to increase the compression ratio. According to the experiments performed on 12 models, the average compression performance of our algorithm is 6.7 bits/vertex, which is a clear improvement over previous methods.

This paper presents a new technique called motion balance filtering, which corrects an unbalanced motion to a balanced one while preserving the original motion characteristics as much as possible. Differently from previous approaches that deal only with the balance of static posture, we solve the problem of balancing a dynamic motion. We achieve dynamic balance by analyzing and controlling the trajectory of the zero moment point (ZMP). Our algorithm consists of three steps. First, it analyzes the ZMP trajectory to find out the duration in which dynamic balance is violated. Dynamic imbalance is identified by the ZMP trajectory segments lying out of the supporting area. Next, the algorithm modifies the ZMP trajectory by projecting it into the supporting area. Finally, it generates the balanced motion that satisfies the new ZMP constraint. This process is formulated as a constrained optimization problem so that the new motion resembles the original motion as much as possible. Experiments prove that our motion balance filtering algorithm is a useful method to add physical realism to a kinematically edited motion.

This paper presents a method to retarget the motion of a character to another in real time. The technique is based on inverse rate control, which computes the changes in joint angles corresponding to the changes in end-effector position. While tracking the multiple end-effector trajectories of the original subject or character, our online motion retargetting also minimizes the joint angle differences by exploiting the kinematic redundancies of the animated model. This method can apply a captured motion to another anthropometry so that it can perform slightly different motion, while preserving the original motion characteristics. Because the above is done online, a real-time performance can be mapped to other characters. Moreover, if the method is used interactively during motion capture session, the feedback of retargetted motion on the screen provides more chances to get satisfactory results. As a by-product, our algorithm can be used to reduce measurement errors in restoring captured motion. The data enhancement improves the accuracy in both joint angles and end-effector positions. Experimental results show that our retargetting algorithm preserves high-frequency details of the original motion quite accurately. Copyright © 2000 John Wiley & Sons, Ltd.

This paper presents a method to retarget the motion of a character to another in real-time. The technique is based on inverse rate control, which compares the changes in joint angles corresponding to the changes in end-effector position. While tracking the multiple end-effector trajectories of the original subject or character, our on-line motion retargetting also minimizes the joint angle differences by exploiting the kinematic redundancies of the animated model. This method can generalize a captured motion for another anthropometry to perform slightly different motion, while preserving the original motion characteristics. Because the above is done in on-line, a real-time performance can be mapped to other characters. Moreover, if the method is used interactively during motion capture session, the feedback of retargetted motion on the screen provides more chances to get satisfactory results. As a by-product, our algorithm can be used to reduce measurement errors in restoring captured motion. The data enhancement improves the accuracy in both joint angles and end-effector positions. Experiments prove that our retargetting algorithm preserves the high frequency details of the original motion quite accurately.

We describe a real-time model of terrain traversal by simulated human agents. Agent navigation includes a variety of simulated sensors, terrain reasoning with behavioral constraints, and detailed simulation of a variety of locomotion techniques. The path through the terrain is incrementally computed by a behavioral reasoning system configuring a behavioral feedback network. A number of sensors acquire information on object range, passageways, obstacles, terrain type, exposure to hostile agents, and so on. The behavioral reasoner weighs this information along with collision avoidance, cost, danger minimization, locomotion types, and other behaviors available to the agent and incrementally attempts to reach a goal location. Since the system is reactive, it can respond to moving obstacles, changing terrain, or unexpected events due to hostile agents or the effects of limited perception. A motor-level component provides general locomotion, including curved path walking and running that work in real-time with human figures.>