Motion Keyframe Interpolation for Any Human Skeleton via Temporally Consistent Point Cloud Sampling and Reconstruction

TL;DR

This paper introduces an unsupervised method called PC-MRL that enables cross-skeleton motion interpolation by learning from point cloud representations, overcoming dataset limitations for various human skeleton configurations.

Contribution

The paper presents a novel unsupervised approach using point cloud sampling and reconstruction for cross-skeleton motion interpolation, expanding applicability beyond fixed skeleton datasets.

Findings

Effective motion interpolation across different skeletons without supervised training.

Successful use of point cloud sampling for skeleton obfuscation and reconstruction.

Improved motion interpolation quality demonstrated through comprehensive experiments.

Abstract

In the character animation field, modern supervised keyframe interpolation models have demonstrated exceptional performance in constructing natural human motions from sparse pose definitions. As supervised models, large motion datasets are necessary to facilitate the learning process; however, since motion is represented with fixed hierarchical skeletons, such datasets are incompatible for skeletons outside the datasets' native configurations. Consequently, the expected availability of a motion dataset for desired skeletons severely hinders the feasibility of learned interpolation in practice. To combat this limitation, we propose Point Cloud-based Motion Representation Learning (PC-MRL), an unsupervised approach to enabling cross-compatibility between skeletons for motion interpolation learning. PC-MRL consists of a skeleton obfuscation strategy using temporal point cloud sampling, and an unsupervised skeleton reconstruction method from point clouds. We devise a temporal point-wise K-nearest neighbors loss for unsupervised learning. Moreover, we propose First-frame Offset Quaternion (FOQ) and Rest Pose Augmentation (RPA) strategies to overcome necessary limitations of our unsupervised point cloud-to-skeletal motion process. Comprehensive experiments demonstrate the effectiveness of PC-MRL in motion interpolation for desired skeletons without supervision from native datasets.