Automatic Motion Generation Based on Path Editing from Motion Capture Data

Abstract

Abstract. In this paper, we present an integrated framework with easy and effective techniques to generate new motions of a character in real-time, using only a short segment of motion data. In this framework, a sequence of segment copies are strung together and then smoothed by a transition method at a junction of two consecutive segments. We use IK thought for the transition to solve the foot-slide problem at the junctions. Given a new motion path, we combine the IK constraints and the sequence of smoothed motion capture data to adjust the human-like model. Based on only a sample motion segment, our method can generate a sequence of motions following an arbitrary path specified by the user. Furthermore, it is easy to implement and can be applied to highly kinetic motions. The experimental results demonstrate our scheme.

A Cyclic Consistency Motion Style Transfer Method Combined with Kinematic Constraints

“…In order to compare the effect of style transfer, this paper compares with Zan [23], Hu [38], Guo et al [39], and Holden et al [22]. Guo et al [39] proposed a style transfer method combined with inverse kinematic constraints.…”

“…In order to compare the effect of style transfer, this paper compares with Zan [23], Hu [38], Guo et al [39], and Holden et al [22]. Guo et al [39] proposed a style transfer method combined with inverse kinematic constraints. First, the motion sequence is aligned through dynamic time warping, and then, the motion sequence is edited by establishing inverse kinematic constraints to realize the motion style transfer.…”

“…Through the above five methods, the elderly style motions are transferred to running motions, and then, the style similarity is compared. From the calculation results of style similarity in Figure 11, it can be seen that the generated movement and content movement of Zan [23] and Guo et al [39] are more similar, and the effect of style transfer is not ideal. The method of this paper and Hu [38] generates relatively small values of similarity between the movement and the style movement, and the effect of style transfer is better.…”