Okan Arikan, David A.
Forsyth. Interactive Motion Generation from Examples.
ACM Transactions on Graphics (ACM SIGGRAPH 2002), Vol:
21, No: 3, pp 483--490, 2002.
Abstract
There are many applications that demand large quantities of natural looking motion. It is difficult to synthesize motion that
looks natural, particularly when it is people who must move. In this paper, we present a framework that generates human motions by
cutting and pasting motion capture data. Selecting a collection of clips that yields an acceptable motion is a combinatorial problem
that we manage as a randomized search of a hierarchy of graphs. This approach can generate motion sequences that satisfy a variety
of constraints automatically. The motions are smooth and human-looking. They are generated in real time so that we can
author complex motions interactively. The algorithm generates multiple motions that satisfy a given set of constraints, allowing
a variety of choices for the animator. It can easily synthesize multiple motions that interact with each other using constraints.
This framework allows the extensive re-use of motion capture data for new purposes.
Constraints: The two yellow arrows and their time stamps (i.e. when the
body has to be at the arrow).
Constraints: The three yellow arrows and their time stamps.
Constraints: The time stamped yellow arrows and time
stamped position constraint on the head to force a
jumping motion.
Constraints: The time stamped yellow
arrows and being lying flat on the ground on the second
yellow arrow at the end of the motion.
Complex multi-mody interactions:
Here, skeletons are
constrained to pass through tacking poses at particular
times and positions. Using this technique we can
generate multiple motions that seem to interact with
each other. However, these motions were synthesized
seperately.
In this movie, the constraints
that we put are indicated with white skeletons. The
colored skeletons are the synthesized motions. The color
of a skeleton changes as we switch from one motion to
another.
