Abstract This paper presents a simple and efficient technique for synthesizing high‐fidelity motions by attaching, or splicing, the upper‐body action of one motion example to the lower‐body locomotion of another. Existing splicing algorithms do little more than copy degrees of freedom (DOFs) from one motion onto another. This naïve DOF replacement can produce unrealistic results because it ignores both physical and stylistic correlations between various joints in the body. Our approach uses spatial and temporal relationships found within the example motions to retain the overall posture of the upper‐body action while adding secondary motion details appropriate to the timing and configuration of the lower body. By decoupling upper‐body action from lower‐body locomotion, our motion synthesis technique allows example motions to be captured independently and later combined to create new natural looking motions. Categories and Subject Descriptors (according to ACM CCS): I.3.7 [Computer Graphics]: Animation

Large motion data sets often contain many variants of the same kind of motion, but without appropriate tools it is difficult to fully exploit this fact. This paper provides automated methods for identifying logically similar motions in a data set and using them to build a continuous and intuitively parameterized space of motions. To find logically similar motions that are numerically dissimilar, our search method employs a novel distance metric to find "close" motions and then uses them as intermediaries to find more distant motions. Search queries are answered at interactive speeds through a precomputation that compactly represents all possibly similar motion segments. Once a set of related motions has been extracted, we automatically register them and apply blending techniques to create a continuous space of motions. Given a function that defines relevant motion parameters, we present a method for extracting motions from this space that accurately possess new parameters requested by the user. Our algorithm extends previous work by explicitly constraining blend weights to reasonable values and having a run-time cost that is nearly independent of the number of example motions. We present experimental results on a test data set of 37,000 frames, or about ten minutes of motion sampled at 60 Hz.

Many popular motion editing methods do not take physical principles into account potentially producing implausible motions. This paper introduces an efficient method for touching up edited motions to improve physical plausibility. We start by estimating a mass distribution consistent with reference motions known to be physically correct. The edited motion is then divided into ground and flight stages and adjusted to enforce appropriate physical laws, for, respectively, zero moment point (ZMP) constraints and correct ballistic trajectory. Unlike previous methods, we do not solve a nonlinear optimization to calculate the adjustment. Instead, closed-form methods are used to construct a hierarchical displacement map which sequentially refines user-specified degrees of freedom at different scales. This is combined with standard methods for kinematic constraint enforcement, yielding an efficient and scalable editing method that allows users to model real human behaviors. The potential of our approach is demonstrated in a number of examples.

Many virtual environments and games must be populated with synthetic characters to create the desired experience. These characters must move with sufficient realism, so as not to destroy the visual quality of the experience, yet be responsive, controllable, and efficient to simulate. In this paper we present an approach to character motion called Snap-Together Motion that addresses the unique demands of virtual environments. Snap-Together Motion (STM) preprocesses a corpus of motion capture examples into a set of short clips that can be concatenated to make continuous streams of motion. The result process is a simple graph structure that facilitates efficient planning of character motions. A user-guided process selects "common" character poses and the system automatically synthesizes multi-way transitions that connect through these poses. In this manner well-connected graphs can be constructed to suit a particular application, allowing for practical interactive control without the effort of manually specifying all transitions.

No abstract available.

In this paper we present a novel method for creating realistic, controllable motion. Given a corpus of motion capture data, we automatically construct a directed graph called a motion graph that encapsulates connections among the database. The motion graph consists both of pieces of original motion and automatically generated transitions. Motion can be generated simply by building walks on the graph. We present a general framework for extracting particular graph walks that meet a user's specifications. We then show how this framework can be applied to the specific problem of generating different styles of locomotion along arbitrary paths.

In this paper we present a method for helping artists make artwork more accessible to casual users. We focus on the specific case of drawings, showing how a small number of drawings can be transformed into a richer object containing an entire family of similar drawings. This object is represented as a simplicial complex approximating a set of valid interpolations in configuration space. The artist does not interact directly with the simplicial complex. Instead, she guides its construction by answering a specially chosen set of yes/no questions. By combining the flexibility of a simplicial complex with direct human guidance, we are able to represent very general constraints on membership in a family. The constructed simplicial complex supports a variety of algorithms useful to an end user, including random sampling of the space of drawings, constrained interpolation between drawings, projection of another drawing into the family, and interactive exploration of the family.