Composable Semi-parametric Modelling for Long-range Motion Generation

Jingwei Xu, Huazhe Xu, Bingbing Ni, Xiaokang Yang, Trevor Darrell

Keywords: Semi-parametric, Long-range, Motion Generation

TL;DR: We propose a semi-parametric model to generate long-range, diverse and visually natural motion sequence.

Abstract: Learning diverse and natural behaviors is one of the longstanding goal for creating intelligent characters in the animated world. In this paper, we propose ``COmposable Semi-parametric MOdelling'' (COSMO), a method for generating long range diverse and distinctive behaviors to achieve a specific goal location. Our proposed method learns to model the motion of human by combining the complementary strengths of both non-parametric techniques and parametric ones. Given the starting and ending state, a memory bank is used to retrieve motion references that are provided as source material to a deep network. The synthesis is performed by a deep network that controls the style of the provided motion material and modifies it to become natural. On skeleton datasets with diverse motion, we show that the proposed method outperforms existing parametric and non-parametric baselines. We also demonstrate the generated sequences are useful as subgoals for actual physical execution in the animated world.