Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset

TL;DR

Motion-X is a large-scale 3D whole-body human motion dataset with detailed annotations, enabling advances in expressive motion generation and 3D human mesh recovery.

Contribution

We developed a scalable, high-precision annotation pipeline and created Motion-X, a comprehensive dataset with 15.6 million 3D pose annotations and semantic labels.

Findings

Annotation pipeline is highly accurate and cost-effective.

Motion-X enhances expressive and diverse motion generation.

Improves 3D human mesh recovery methods.

Abstract

In this paper, we present Motion-X, a large-scale 3D expressive whole-body motion dataset. Existing motion datasets predominantly contain body-only poses, lacking facial expressions, hand gestures, and fine-grained pose descriptions. Moreover, they are primarily collected from limited laboratory scenes with textual descriptions manually labeled, which greatly limits their scalability. To overcome these limitations, we develop a whole-body motion and text annotation pipeline, which can automatically annotate motion from either single- or multi-view videos and provide comprehensive semantic labels for each video and fine-grained whole-body pose descriptions for each frame. This pipeline is of high precision, cost-effective, and scalable for further research. Based on it, we construct Motion-X, which comprises 15.6M precise 3D whole-body pose annotations (i.e., SMPL-X) covering 81.1K motion sequences from massive scenes. Besides, Motion-X provides 15.6M frame-level whole-body pose descriptions and 81.1K sequence-level semantic labels. Comprehensive experiments demonstrate the accuracy of the annotation pipeline and the significant benefit of Motion-X in enhancing expressive, diverse, and natural motion generation, as well as 3D whole-body human mesh recovery.