Generative Tweening: Long-term Inbetweening of 3D Human Motions

TL;DR

This paper presents a biomechanically constrained generative adversarial network for long-term inbetweening of 3D human motions, enabling automatic synthesis of complex, realistic animations from sparse keyframes with user control.

Contribution

It introduces a novel two-stage deep learning approach with biomechanical constraints and a Motion DNA scheme for diverse, controllable long-term human motion generation.

Findings

Robust performance across 79 motion classes.

Ability to generate diverse motion outputs.

Effective long-term inbetweening from sparse keyframes.

Abstract

The ability to generate complex and realistic human body animations at scale, while following specific artistic constraints, has been a fundamental goal for the game and animation industry for decades. Popular techniques include key-framing, physics-based simulation, and database methods via motion graphs. Recently, motion generators based on deep learning have been introduced. Although these learning models can automatically generate highly intricate stylized motions of arbitrary length, they still lack user control. To this end, we introduce the problem of long-term inbetweening, which involves automatically synthesizing complex motions over a long time interval given very sparse keyframes by users. We identify a number of challenges related to this problem, including maintaining biomechanical and keyframe constraints, preserving natural motions, and designing the entire motion sequence holistically while considering all constraints. We introduce a biomechanically constrained generative adversarial network that performs long-term inbetweening of human motions, conditioned on keyframe constraints. This network uses a novel two-stage approach where it first predicts local motion in the form of joint angles, and then predicts global motion, i.e. the global path that the character follows. Since there are typically a number of possible motions that could satisfy the given user constraints, we also enable our network to generate a variety of outputs with a scheme that we call Motion DNA. This approach allows the user to manipulate and influence the output content by feeding seed motions (DNA) to the network. Trained with 79 classes of captured motion data, our network performs robustly on a variety of highly complex motion styles.