GUESS：用于文本驱动的人体动作生成的渐进式丰富合成
GUESS:GradUally Enriching SyntheSis for Text-Driven Human Motion Generation
AI总结：
本文提出一种基于级联扩散的文本驱动人体动作生成框架GUESS，通过递归抽象关节分组实现多粒度骨架表示，并采用多阶段生成与动态多条件融合机制，在大规模数据集上大幅超越现有方法。
摘要：
在本文中，我们提出了一种用于文本驱动的人体动作生成的新型级联扩散生成框架，该框架采用了一种名为 GradUally Enriching SyntheSis（简称 GUESS）的策略。该策略通过将详细骨架中语义相近的身体关节分组在一起，然后将每个这样的关节组替换为单个身体部位节点来设定生成目标。这种操作递归地将人体姿态抽象为多个粒度级别上越来越粗糙的骨架。随着抽象级别的逐渐提高，人体动作变得越来越简洁和稳定，这极大地有利于跨模态动作合成任务。整个文本驱动的人体动作生成问题随后被划分为多个抽象级别，并通过一个带有级联潜在扩散模型的多阶段生成框架来解决：初始生成器首先根据给定的文本描述生成最粗糙的人体动作猜测；然后，一系列后续生成器根据文本描述和先前合成的结果逐渐丰富动作细节。值得注意的是，我们进一步将 GUESS 与所提出的动态多条件融合机制相结合，以动态平衡不同生成阶段中给定文本条件和合成粗糙动作提示的协同效应。在大规模数据集上的大量实验验证了 GUESS 在准确性、真实性和多样性方面大幅优于现有的最先进方法。代码可在 https://github.com/Xuehao-Gao/GUESS 获取。
英文摘要：
In this paper, we propose a novel cascaded diffusion-based generative framework for text-driven human motion synthesis, which exploits a strategy named GradUally Enriching SyntheSis (GUESS as its abbreviation). The strategy sets up generation objectives by grouping body joints of detailed skeletons in close semantic proximity together and then replacing each of such joint group with a single body-part node. Such an operation recursively abstracts a human pose to coarser and coarser skeletons at multiple granularity levels. With gradually increasing the abstraction level, human motion becomes more and more concise and stable, significantly benefiting the cross-modal motion synthesis task. The whole text-driven human motion synthesis problem is then divided into multiple abstraction levels and solved with a multi-stage generation framework with a cascaded latent diffusion model: an initial generator first generates the coarsest human motion guess from a given text description; then, a series of successive generators gradually enrich the motion details based on the textual description and the previous synthesized results. Notably, we further integrate GUESS with the proposed dynamic multi-condition fusion mechanism to dynamically balance the cooperative effects of the given textual condition and synthesized coarse motion prompt in different generation stages. Extensive experiments on large-scale datasets verify that GUESS outperforms existing state-of-the-art methods by large margins in terms of accuracy, realisticness, and diversity. Code is available at https://github.com/Xuehao-Gao/GUESS.
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。
