arXiv 2605.209552026-05-20cs.CV

DrawMotion: 通过自由手绘生成3D人体动作

DrawMotion: Generating 3D Human Motions by Freehand Drawing

Beijing University of Posts and Telecommunications（北京邮电大学）；University of Science and Technology of China（中国科学技术大学）；NLP Lab, School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院自然语言处理实验室）；National University of Singapore（新加坡国立大学）；Tsinghua University（清华大学）；The Institute of AI (TeleAI), China Telecom（中国电信人工智能研究院）；Northwestern Polytechnical University（西北工业大学）

Tao Wang, Lei Jin, Zhihua Wu, Qiaozhi He, Jiaming Chu, Yu Cheng, Junliang Xing, Jian Zhao, Shuicheng Yan, Li Wang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究提出DrawMotion，一种基于扩散模型的框架，通过自由手绘和文本条件生成3D人体动作，减少用户输入时间，提升生成精度。

摘要：

文本到动作生成，即通过文本描述生成人体动作，面临用户难以通过文本精确表达意图的挑战。为了解决这一问题，本文介绍了DrawMotion，一种高效的扩散基框架，适用于多条件场景。DrawMotion基于传统文本条件和新的手绘条件生成动作，分别提供语义和空间控制。具体而言，我们从三个方面解决细粒度动作生成任务：1) 自由手绘条件。为了准确捕捉用户意图而不需繁琐的文本输入，我们开发了算法自动在不同数据集格式中生成手绘简笔画；2) 多条件融合。我们提出了一个多条件模块（MCM），整合到扩散过程中，使模型能够利用所有可能的条件组合，同时比传统方法减少计算复杂性；3) 训练自由引导。值得注意的是，DrawMotion中的MCM确保其中间特征位于连续空间中，允许分类器引导梯度更新特征，从而使生成的动作与用户意图对齐，同时保持保真度。定量实验和用户研究表明，自由手绘方法在生成与想象一致的动作时，可将用户时间减少约46.7%。代码、演示和相关数据可在https://github.com/InvertedForest/DrawMotion上公开获取。

英文摘要：

Text-to-motion generation, which translates textual descriptions into human motions, faces the challenge that users often struggle to precisely convey their intended motions through text alone. To address this issue, this paper introduces DrawMotion, an efficient diffusion-based framework designed for multi-condition scenarios. DrawMotion generates motions based on both a conventional text condition and a novel hand-drawing condition, which provide semantic and spatial control over the generated motions, respectively. Specifically, we tackle the fine-grained motion generation task from three perspectives: 1) freehand drawing condition. To accurately capture users' intended motions without requiring tedious textual input, we develop an algorithm to automatically generate hand-drawn stickman sketches across different dataset formats; 2) multi-condition fusion. We propose a Multi-Condition Module (MCM) that is integrated into the diffusion process, enabling the model to exploit all possible condition combinations while reducing computational complexity compared to conventional approaches; and 3) training-free guidance. Notably, the MCM in DrawMotion ensures that its intermediate features lie in a continuous space, allowing classifier-guidance gradients to update the features and thereby aligning the generated motions with user intentions while preserving fidelity. Quantitative experiments and user studies demonstrate that the freehand drawing approach reduces user time by approximately 46.7% when generating motions aligned with their imagination. The code, demos, and relevant data are publicly available at https://github.com/InvertedForest/DrawMotion.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。