This paper presents an inverse kinematics system based on a learned model of human poses. Given a set of constraints, our system can produce the most likely pose satisfying those constraints, in realtime. Training the model on different input data leads to different styles of IK. The model is represented as a probability distribution over the space of all possible poses. This means that our IK system can generate any pose, but prefers poses that are most similar to the space of poses in the training data. We represent the probability with a novel model called a Scaled Gaussian Process Latent Variable Model. The parameters of the model are all learned automatically; no manual tuning is required for the learning component of the system. We additionally describe a novel procedure for interpolating between styles. Our style-based

This paper presents a novel physics-based representation of realistic character motion. The dynamical model incorporates several factors of locomotion derived from the biomechanical literature, including relative preferences for using some muscles more than others, elastic mechanisms at joints due to the mechanical properties of tendons, ligaments, and muscles, and variable stiffness at joints depending on the task. When used in a spacetime optimization framework, the parameters of this model define a wide range of styles of natural human movement.

This paper introduces an approach to performance animation that employs video cameras and a small set of retro-reflective markers to create a low-cost, easy-to-use system that might someday be practical for home use. The low-dimensional control signals from the user's performance are supplemented by a database of pre-recorded human motion. At run time, the system automatically learns a series of local models from a set of motion capture examples that are a close match to the marker locations captured by the cameras. These local models are then used to reconstruct the motion of the user as a full-body animation. We demonstrate the power of this approach with real-time control of six different behaviors using two video cameras and a small set of retro-reflective markers. We compare the resulting animation to animation from commercial motion capture equipment with a full set of markers.

Figure 1: Our style translation system transforms a normal walk (TOP) into a sneaky crouch (MIDDLE) and a sideways shuffle (BOTTOM). Style translation is the process of transforming an input motion into a new style while preserving its original content. This problem is motivated by the needs of interactive applications which require rapid processing of captured performances. Our solution learns to translate by analyzing differences between performances of the same content in input and output styles. It relies on a novel correspondence algorithm to align motions and a linear time-invariant model to represent stylistic differences. Once the model is estimated with system identification, the system is capable of translating streaming input with simple linear operations at each frame.

Figure 1: Examples from our test set of motions. The left two images are natural (motion capture data). The two images to the right are unnatural (badly edited and incompletely cleaned motion). Joints that are marked in red-yellow were detected as having unnatural motion. Frames for these images were selected by the method presented in [Assa et al. 2005]. In this paper, we investigate whether it is possible to develop a measure that quantifies the naturalness of human motion (as defined by a large database). Such a measure might prove useful in verifying that a motion editing operation had not destroyed the naturalness of a motion capture clip or that a synthetic motion transition was within the space of those seen in natural human motion. We explore the performance of mixture of Gaussians (MoG), hidden Markov models (HMM), and switching linear dynamic systems (SLDS) on this problem. We use each of these statistical models alone and as part of an ensemble of smaller statistical models. We also implement a Naive Bayes (NB) model for a baseline comparison. We test these techniques on motion capture data held out from a database, keyframed motions, edited motions, motions with noise added, and synthetic motion transitions. We present the results as receiver operating characteristic (ROC) curves and compare the results to the judgments made by subjects in a user study.

The reuse of human motion capture data to create new, realistic motions by applying morphing and blending techniques has become an important issue in computer animation. This requires the identification and extraction of logically related motions scattered within some data set. Such content-based retrieval of motion capture data, which is the topic of this paper, constitutes a difficult and timeconsuming problem due to significant spatio-temporal variations between logically related motions. In our approach, we introduce various kinds of qualitative features describing geometric relations between specified body points of a pose and show how these features induce a time segmentation of motion capture data streams. By incorporating spatio-temporal invariance into the geometric features and adaptive segments, we are able to adopt efficient indexing methods allowing for flexible and efficient content-based retrieval and browsing in huge motion capture databases. Furthermore, we obtain an efficient preprocessing method substantially accelerating the cost-intensive classical dynamic time warping techniques for the time alignment of logically similar motion data streams. We present experimental results on a test data set of more than one million frames, corresponding to 180 minutes of motion. The linearity of our indexing algorithms guarantees the scalability of our results to much larger data sets.

Figure 1: Animations synthesized by our motion interpolation in a 5D parametric space. One parameter changes the style of motion from rough to delicate as shown by the bar indicator. The other four parameters are the heights and widths of two successive steps of stairs for gait motions, and the 2D start and end locations of the box for lifting motions. None of the motions required post-cleaning of foot- or hand-sliding. 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 this paper, we propose an example-based approach to on-line locomotion synthesis. Our approach consists of two parts: motion analysis and motion synthesis. In the motion analysis part, an unlabeled motion sequence is first decomposed into motion segments, exploiting the behavior of the COM (center of mass) trajectory of the performer. Those motion segments are subsequently classified into groups of motion segments such that the same group of motion segments share an identical footstep pattern. Finally, we construct a hierarchical motion transition graph by representing these groups and their connectivity to other groups as nodes and edges, respectively. The coarse level of this graph models locomotive motions and their transitions, and the fine level mainly captures the cyclic nature of locomotive motions. In the motion synthesis part, given a stream of motion specifications in an on-line manner, the motion transition graph is traversed while blending the motion segments to synthesize a motion at a node, one by one, guided by the motion specifications. Our main contributions are the motion labeling scheme and a new motion model, embodied by the hierarchical motion transition graph, which together enable not only artifact-free motion blending but also seamless motion transition.

Figure 1: Optimal and sub-optimal solutions for walking a given distance (left) and for picking up an object (right). Many compelling applications would become feasible if novice users had the ability to synthesize high quality human motion based only on a simple sketch and a few easily specified constraints. We approach this problem by representing the desired motion as an interpolation of two time-scaled paths through a motion graph. The graph is constructed to support interpolation and pruned for efficient search. We use an anytime version of A ∗ search to find a globally optimal solution in this graph that satisfies the user’s specification. Our approach retains the natural transitions of motion graphs and the ability to synthesize physically realistic variations provided by interpolation. We demonstrate the power of this approach by synthesizing optimal or near optimal motions that include a variety of behaviors in a single motion.

Temporal segmentation of human motion into actions is a crucial step for understanding and building computational models of human motion. Several issues contribute to the challenge of this task. These include the large variability in the temporal scale and periodicity of human actions, as well as the exponential nature of all possible movement combinations. We formulate the temporal segmentation problem as an extension of standard clustering algorithms. In particular, this paper proposes Aligned Cluster Analysis (ACA), a robust method to temporally segment streams of motion capture data into actions. ACA extends standard kernel k-means clustering in two ways: (1) the cluster means contain a variable number of features, and (2) a dynamic time warping (DTW) kernel is used to achieve temporal invariance. Experimental results, reported on synthetic data and the Carnegie Mellon Motion Capture database, demonstrate its effectiveness.