ParTY：面向富有表现力文本到动作合成的部位引导
ParTY: Part-Guidance for Expressive Text-to-Motion Synthesis
其「先分部位生成、再以部位引导整体生成」的两阶段思路与部位感知的文本嵌入对齐，可迁移到细粒度可控的人体动作/姿态生成与部位级文本定位任务。
原文依据 Part-Guided Network, which first generates part motions to obtain part guidance, then uses it to generate holistic motions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论文本到动作合成旨在根据文本描述生成自然且富有表现力的人体动作。现有方法主要关注从文本描述生成整体动作，但难以准确反映涉及特定身体部位的动作。近期的分部位动作生成方法试图解决这一问题，却面临两个关键局限：(i) 缺乏将文本语义与各个身体部位显式对齐的机制；(ii) 由于整合独立生成的各部位动作，往往生成不连贯的全身动作。为克服这些问题并解决现有方法中的根本性权衡，我们提出 ParTY，一个在生成连贯全身动作的同时增强部位表现力的新框架。ParTY 包含：(1) 部位引导网络，首先生成部位动作以获得部位引导，再利用该引导生成整体动作；(2) 部位感知文本接地，对文本嵌入进行多样化变换并将其与每个身体部位恰当对齐；(3) 整体-部位融合，自适应地融合整体动作与部位动作。大量实验（包括部位级与连贯性级评估）表明，ParTY 相较此前方法取得了显著提升。
英文原文摘要 1301 字符
Text-to-motion synthesis aims to generate natural and expressive human motions from textual descriptions. While existing approaches primarily focus on generating holistic motions from text descriptions, they struggle to accurately reflect actions involving specific body parts. Recent part-wise motion generation methods attempt to resolve this but face two critical limitations: (i) they lack explicit mechanisms for aligning textual semantics with individual body parts, and (ii) they often generate incoherent full-body motions due to integrating independently generated part motions. To overcome these issues and resolve the fundamental trade-off in existing methods, we propose ParTY, a novel framework that enhances part expressiveness while generating coherent full-body motions. ParTY comprises: (1) Part-Guided Network, which first generates part motions to obtain part guidance, then uses it to generate holistic motions; (2) Part-aware Text Grounding, which diversely transforms text embeddings and appropriately aligns them with each body part; and (3) Holistic-Part Fusion, which adaptively fuses holistic motions and part motions. Extensive experiments, including part-level and coherence-level evaluations, demonstrate that ParTY achieves substantial improvements over previous methods.