ReMoGen：通过多源数据模块化学习的实时人体交互到反应生成
ReMoGen: Real-time Human Interaction-to-Reaction Generation via Modular Learning from Diverse Data
把大规模单人动作数据学到的通用运动先验，通过独立训练的 Meta-Interaction 模块迁移到人-人、人-场景等数据稀缺的交互域，并用帧级 Segment Refinement 在在线推理时融合新观测——这套「通用先验 + 轻量域适配 + 帧级精修」的模块化范式可直接复用到实时人体动作/反应生成与虚拟人驱动。
原文依据 a universal motion prior learned from large-scale single-person motion datasets and adapts it to target interaction domains
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论真实环境中的类人行为本质上是交互性的，个体的运动会受到周围智能体与场景的塑造。这种能力对于虚拟化身、交互式动画以及人-机器人协作等应用至关重要。本文研究实时人体交互到反应生成，即根据动态的多源线索（包括他人的动作、场景几何以及可选的高层语义输入）生成自我主体的未来运动。该任务面临根本性挑战：(i) 交互数据有限且碎片化，分散在异构的单人、人-人、人-场景等域中；(ii) 在持续在线交互过程中需要产生低延迟且高保真的运动响应。为应对这些挑战，我们提出 ReMoGen（反应运动生成），一个用于实时交互到反应生成的模块化学习框架。ReMoGen 利用从大规模单人运动数据集中学习到的通用运动先验，并通过独立训练的 Meta-Interaction 模块将其适配到目标交互域，从而在数据稀缺与异构监督下实现稳健的泛化。为支持响应式在线交互，ReMoGen 采用分段级生成，并结合一个轻量的帧级分段精修模块，在帧级别融入新观测到的线索，从而在无需昂贵的全序列推理的情况下同时提升响应性与时序连贯性。在人-人、人-场景以及混合模态交互设置上的大量实验表明，ReMoGen 能够产生高质量、连贯且响应及时的反应，并在多样的交互场景中有效泛化。
英文原文摘要 1752 字符
Human behaviors in real-world environments are inherently interactive, with an individual's motion shaped by surrounding agents and the scene. Such capabilities are essential for applications in virtual avatars, interactive animation, and human-robot collaboration. We target real-time human interaction-to-reaction generation, which generates the ego's future motion from dynamic multi-source cues, including others' actions, scene geometry, and optional high-level semantic inputs. This task is fundamentally challenging due to (i) limited and fragmented interaction data distributed across heterogeneous single-person, human-human, and human-scene domains, and (ii) the need to produce low-latency yet high-fidelity motion responses during continuous online interaction. To address these challenges, we propose ReMoGen (Reaction Motion Generation), a modular learning framework for real-time interaction-to-reaction generation. ReMoGen leverages a universal motion prior learned from large-scale single-person motion datasets and adapts it to target interaction domains through independently trained Meta-Interaction modules, enabling robust generalization under data-scarce and heterogeneous supervision. To support responsive online interaction, ReMoGen performs segment-level generation together with a lightweight Frame-wise Segment Refinement module that incorporates newly observed cues at the frame level, improving both responsiveness and temporal coherence without expensive full-sequence inference. Extensive experiments across human-human, human-scene, and mixed-modality interaction settings show that ReMoGen produces high-quality, coherent, and responsive reactions, while generalizing effectively across diverse interaction scenarios.