Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data

TL;DR

This paper introduces MotionMillion, the largest human motion dataset, and a scalable model that achieves zero-shot generalization in text-to-motion generation, significantly advancing the field.

Contribution

It presents MotionMillion, a large-scale dataset, and a comprehensive benchmark, along with a scalable model that demonstrates strong zero-shot generalization capabilities.

Findings

Achieved state-of-the-art zero-shot motion generation performance.

Demonstrated strong out-of-domain and complex motion generalization.

Provided a new large-scale dataset and evaluation framework.

Abstract

Generating diverse and natural human motion sequences based on textual descriptions constitutes a fundamental and challenging research area within the domains of computer vision, graphics, and robotics. Despite significant advancements in this field, current methodologies often face challenges regarding zero-shot generalization capabilities, largely attributable to the limited size of training datasets. Moreover, the lack of a comprehensive evaluation framework impedes the advancement of this task by failing to identify directions for improvement. In this work, we aim to push text-to-motion into a new era, that is, to achieve the generalization ability of zero-shot. To this end, firstly, we develop an efficient annotation pipeline and introduce MotionMillion-the largest human motion dataset to date, featuring over 2,000 hours and 2 million high-quality motion sequences. Additionally, we propose MotionMillion-Eval, the most comprehensive benchmark for evaluating zero-shot motion generation. Leveraging a scalable architecture, we scale our model to 7B parameters and validate its performance on MotionMillion-Eval. Our results demonstrate strong generalization to out-of-domain and complex compositional motions, marking a significant step toward zero-shot human motion generation. The code is available at https://github.com/VankouF/MotionMillion-Codes.