Abstract Acanthus ornaments frequently adorn Western architectural designs. The placement of these motifs varies according to the decorative object, with some having motifs arranged in a grid pattern. In this study, we propose a procedural modeling system aimed at generating acanthus ornaments on a planar surface. The proposed approach initially establishes the layout of boundary grids for acanthus motifs by subdividing the target surface into nonuniform grids. Subsequently, the medial axis line of the acanthus motif is generated to optimally conform to each boundary grid, employing a parameterized representation of deformable motifs. The three‐dimensional motif shapes are ultimately constructed from the medial axis, with the shape parameters adjusted to improve aesthetic appeal. The proposed system generates various acanthus ornaments through rule‐based layout subdivisions, offering users the option to select their preferred design while adjusting the motif shapes with a few manual parameters.

The texture upsampling technique reduces the memory and manual labor required to create a high-definition texture by procedurally increasing the image resolution on the fly. We propose a real-time texture upsampling technique that utilizes an underlying fractal structure of surface textures found in natural phenomena, such as stone surfaces, tree bark, and animal skin. Our method encodes the source texture by a fractal compression technique in the authoring process. The cross-scale correspondences between two mipmap layers are encoded as compact fractal codes and packed in three types of GPU-friendly formats. The runtime computation increases the resolution of encoded textures by recursively applying fractal decoding. Owing to the concurrent data structures, texture upsampling by any power of 2 is efficiently executed on GPUs. Furthermore, we propose an iterative algorithm to refine the fractal code, thus improving upsampling quality. We demonstrate the effectiveness of our proposed algorithm by synthesizing a high-resolution texture with semi-random patterns.

Roses fascinate people in several types of visual media such as movies and games. Although the beauty of roses is attributed to the underlying botanical structure and skillful pruning, the conventional modeling method does not explicitly consider the tree shape change with artificial care. We propose a procedural method for modeling the branching structure of well-maintained shrub roses. The branch generation rules are derived to reproduce the characteristics of the ideal tree shape during the blooming season, leveraging both the species-specific growth model and artificial pruning applied appropriately throughout the year. Our system enables intuitive control to change the tree shape by tweaking several parameters. These manually set parameters are designed to represent the differences between rose varieties and mimic manual pruning that reflects the intentions of gardeners. We demonstrate the usability of our method through several experiments.

Abstract Gestural animations in the amusement or entertainment field often require rich expressions; however, it is still challenging to synthesize characteristic gestures automatically. Although style transfer based on a neural network model is a potential solution, existing methods mainly focus on cyclic motions such as gaits and require re‐training in adding new motion styles. Moreover, their per‐pose transformation cannot consider the time‐dependent features, and therefore motion styles of different periods and timings are difficult to be transferred. This limitation is fatal for the gestural motions requiring complicated time alignment due to the variety of exaggerated or intentionally performed behaviors. This study introduces a context‐based style transfer of gestural motions with neural networks to ensure stable conversion even for exaggerated, dynamically complicated gestures. We present a model based on a vision transformer for transferring gestures' content and style features by time‐segmenting them to compose tokens in a latent space. We extend this model to yield the probability of swapping gestures' tokens for style‐transferring. A transformer model is suited to semantically consistent matching among gesture tokens, owing to the correlation with spoken words. The compact architecture of our network model requires only a small number of parameters and computational costs, which is suitable for real‐time applications with an ordinary device. We introduce loss functions provided by the restoration error of identically and cyclically transferred gesture tokens and the similarity losses of content and style evaluated by splicing features inside the transformer. This design of losses allows unsupervised and zero‐shot learning, by which the scalability for motion data is obtained. We comparatively evaluated our style transfer method, mainly focusing on expressive gestures using our dataset captured for various scenarios and styles by introducing new error metrics tailored for gestures. Our experiment showed the superiority of our method in numerical accuracy and stability of style transfer against the existing methods.

A clip of character motion can be adapted to a change in environment or to another character of a different body size via a numerical optimization with several tasks including the objective of movement and physical constraints. Conventional methods, however, lack the design flexibility of such adaptation tasks because of the simple problem formulation. We propose a motion adaptation framework based on a cascaded series of quadratic programs. Our system introduces a layered structure of strictly prioritized tasks, each layer of which comprises arbitrary types of equality and inequality tasks. The cascaded solver identifies the optimal solution in each layer without affecting the fulfillment of the higher layer tasks. The stable computation of the cascaded optimization supports the intuitive design of the spacetime tasks even for novice users. The capability of our method was demonstrated through several experiments of motion adaptation with prioritized inequality tasks, such as environmental adaptation and adaptation of interactive behavior between two characters.

This paper describes a prototype self-training system for tennis forehand shots that allows trainees to practice their motion forms by themselves. Our system uses a motion capture device to record a trainee's motion, and visualizes the differences between the features of the trainee's motion and the correct motion as performed by an expert. This system enables trainees to understand the errors in their motion and how to reduce or eliminate them. In this study, we classified the motion features and corresponding visualization methods using one-dimensional spatial, rotational, and temporal features based on the key sporting poses. We also developed a statistical model for the motion features, allowing the system to assess and prioritize all features of a trainee's motion. This research focuses on the motion of a tennis forehand shot and evaluates our prototype through several user experiments.

Dynamic skin deformation is vital for creating life-like characters, and its real-time computation is in great demand in interactive applications. We propose a practical method to synthesize plausible and dynamic skin deformation based on a helper bone rig. This method builds helper bone controllers for the deformations caused not only by skeleton poses but also secondary dynamics effects. We introduce a state-space model for a discrete time linear time-invariant system that efficiently maps the skeleton motion to the dynamic movement of the helper bones. Optimal transfer of nonlinear, complicated deformations, including the effect of soft-tissue dynamics, is obtained by learning the training sequence consisting of skeleton motions and corresponding skin deformations. Our approximation method for a dynamics model is highly accurate and efficient owing to its low-rank property obtained by a sparsity-oriented nuclear norm optimization. The resulting linear model is simple enough to easily implement in the existing workflows and graphics pipelines. We demonstrate the superior performance of our method compared to conventional dynamic skinning in terms of computational efficiency including LOD controls, stability in interactive controls, and flexible expression in deformations.

Helper bone system has been widely used in real-time applications to synthesize high-quality skin deformation with linear blend skinning. Even though this technique provides a flexible yet efficient synthesis for a variety of expressive skin deformations, rigging with helper bones is still a labor-intensive process. In this study, we propose a novel method for building helper bone rigs from examples. We used multiple pairs of skeleton pose and desired skin shapes for our system. First, the system estimates the optimal skinning weights and helper bone transformations to reconstruct each example shape. Next, we construct a regression model which maps a primary skeleton pose to the helper bone transformations. The regression model enables a procedural control over the helper bones according to the primary skeleton. This is done at a lower computational cost and memory footprint. In addition, artists can edit the regression coefficient of the helper bone controller to modify deformation behavior. We demonstrate our system's potential by synthesizing stylized skin deformations in real-time.

This paper presents a practical system for synthesizing gait animation in game environments. As well as improving the reality of animation, we should improve the efficiency and the maneuverability of the character, both of which are essential for interactive games. Our system supplies these practical demands by integrating a motion interpolation technique and a sampling-based control mechanism. We introduce a parameterized looped motion data structure, called a motion ring, for synthesizing a variety of cyclic motions. A continuous gait motion is synthesized by circulating through the motion ring while the interpolation parameter is adaptively controlled according to the terrain condition. The gait controller uses a sampling-based precomputation technique which efficiently searches natural foot contact on terrain of an arbitrary surface shape. The interpolation parameter is also controlled to obey the user control within the duration of quarter gait cycle. Although our system slightly sacrifices the physical correctness of the synthesized motion in order to quickly respond to user input, critical visual artifacts such as foot-skating and jerky movement are prevented. We demonstrate the efficiency and versatility of our integrated system by interactively navigating the character on complex, uneven terrain.

We develop a novel system to concatenate motions with a smooth transition involving natural, redundant movements which cannot be obtained using traditional motion blending technique. Our basic idea is to apply a spline interpolation in a linear subspace in which each input motion is represented as a low-dimensional curve. By connecting the curves via a spline interpolation, a transition motion is synthesized according to a shape of the spline curve while preserving correlations among joints of input motions. Our system allows users to create a variety of transition motions with simple control of the spline parameters.

Interactive animation systems often use a level-of-detail (LOD) control to reduce the computational cost by eliminating unperceivable details of the scene. Most methods employ a multiresolutional representation of animation and geometrical data, and adaptively change the accuracy level according to the importance of each character. Multilinear analysis provides the efficient representation of multidimensional and multimodal data, including human motion data, based on statistical data correlations. This paper proposes a LOD control method of motion synthesis with a multilinear model. Our method first extracts a small number of principal components of motion samples by analyzing three-mode correlations among joints, time, and samples using high-order singular value decomposition. A new motion is synthesized by interpolating the reduced components using geostatistics, where the prediction accuracy of the resulting motion is controlled by adaptively decreasing the data dimensionality. We introduce a hybrid algorithm to optimize the reduction size and computational time according to the distance from the camera while maintaining visual quality. Our method provides a practical tool for creating an interactive animation of many characters while ensuring accurate and flexible controls at a modest level of computational cost.

Abstract This paper proposes a psychological model for simulating pedestrian behaviors in a crowded space. Our decision‐making scheme controls plausible avoidance behavior depending on the positional relations among surrounding persons, on the basis of a two‐stage personal space and a virtual memory structure as proposed in social psychology. Our system determines pedestrian walking speed with the crowd density to imitate the measured data in urban engineering, and automatically generates plausible motions of the individual pedestrian by composing a locomotion graph with motion capture data. Our approach based on psychology and a variety of actual measurements can increase the accuracy of simulation at both the micro and macro levels. Copyright © 2005 John Wiley & Sons, Ltd.

A common motion interpolation technique for realistic human animation is to blend similar motion samples with weighting functions whose parameters are embedded in an abstract space. Existing methods, however, are insensitive to statistical properties, such as correlations between motions. In addition, they lack the capability to quantitatively evaluate the reliability of synthesized motions. This paper proposes a method that treats motion interpolations as statistical predictions of missing data in an arbitrarily definable parametric space. A practical technique of geostatistics, called universal kriging, is then introduced for statistically estimating the correlations between the dissimilarity of motions and the distance in the parametric space. Our method statistically optimizes interpolation kernels for given parameters at each frame, using a pose distance metric to efficiently analyze the correlation. Motions are accurately predicted for the spatial constraints represented in the parametric space, and they therefore have few undesirable artifacts, if any. This property alleviates the problem of spatial inconsistencies, such as foot-sliding, that are associated with many existing methods. Moreover, numerical estimates for the reliability of predictions enable motions to be adaptively sampled. Since the interpolation kernels are computed with a linear system in real-time, motions can be interactively edited using various spatial controls.

We propose a method for creating human movements by imposing positional constraints of end-effectors at multiple key-frame. We introduce hierarchical reinforcement learning for efficiently searching postures at each key-frame among the huge number of possible candidates. The mechanical structures of virtual characters are also hierarchically decomposed so as to suit the learning mechanism, and each hierarchy prepares templates of discretely sampled postures for narrowing down the searching space. Our method automatically generates complicated sequential movements so that the resulting motions optimize dynamic manipulability for enhancing naturalness of realistic human behaviors.

This paper proposes a method for creating human movements by imposing positional constraints of end-effectors at multiple key-frames. We introduce hierarchical reinforcement learning for efficiently searching postures at each key-frame among the huge number of possible candidates. The mechanical structures of virtual characters are also hierarchically decomposed so as to suit the learning mechanism, and each hierarchy prepares templates of discretely sampled postures for narrowing down the searching space. Our method automatically generates complex movements so that the resulting motions are globally optimized for a whole sequence.