Geostatistical motion interpolation

Abstract

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. AbstractA 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.

Simulation of Human Motion Data using Short‐Horizon Model‐Predictive Control

“…While McSim could incorporate a precomputed feedforward control signal, it produces plausible motions without precomputation. This enables it to be coupled with kinematic motion synthesis techniques [MK05,MP07] to track newly created 2D or 3D motions at run-time.…”

Interactive Demonstration of Pointing Gestures for Virtual Trainers

“…The challenge is to determine the weight values which will lead to stroke locations as close as possible to the (p,q) target. A typical approach is to adjust the kernel functions B i in order to best address the parameterization and spatial constraints [14] [5]. However pre-computation of the weights is required making this approach less suitable for interactive systems and in any case it is not possible to guarantee precise placements.…”

Motion Pattern Encapsulation for Data-Driven Constraint-Based Motion Editing

“…Datadriven approaches rely on mocap data to restrict the solution space of naturallooking motions. Motion graphs and motion interpolation are used to produce new motions from a database [13,14,15]. These techniques are not able to handle end-effector constraints that are not represented in the motion database.…”