邁向零樣本：基於百萬級數據的運動生成研究

摘要

基於文本描述生成多樣且自然的人體運動序列，是計算機視覺、圖形學及機器人領域中一項基礎且具挑戰性的研究課題。儘管該領域已取得顯著進展，現有方法在零樣本泛化能力方面仍面臨諸多挑戰，這主要歸因於訓練數據集的規模有限。此外，缺乏全面的評估框架也阻礙了該任務的進一步發展，因其未能明確指出改進方向。本研究旨在將文本到運動生成推向一個新紀元，即實現零樣本泛化能力。為此，我們首先開發了一套高效的註釋流程，並引入了迄今為止最大的人體運動數據集——MotionMillion，該數據集包含超過2000小時、200萬條高質量運動序列。同時，我們提出了MotionMillion-Eval，這是最全面的零樣本運動生成評估基準。利用可擴展的架構，我們將模型參數擴展至70億，並在MotionMillion-Eval上驗證了其性能。實驗結果表明，我們的模型在域外及複雜組合運動上展現出強大的泛化能力，標誌著零樣本人體運動生成邁出了重要一步。相關代碼已公開於https://github.com/VankouF/MotionMillion-Codes。

English

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.

邁向零樣本：基於百萬級數據的運動生成研究

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

摘要

Support