提出ARMFlow框架，实现3D人体反应生成的高精度、低延迟在线生成。
ARMFlow: AutoRegressive MeanFlow for Online 3D Human Reaction Generation
- 基于均值流架构，用因果编码器与MLP速度预测器建模动作时序依赖。
- 单步推理下FID比现有在线方法低30%，在部分条件约束下达离线最优性能。
- 引入自举上下文编码缓解误差累积，适合实时交互场景应用。
3D人体反应生成面临三大挑战：高运动保真度、实时推理和在线场景下的自回归适应性。现有方法难以同时满足。我们提出ARMFlow，一种基于均值流的自回归框架，通过因果上下文编码器和MLP速度预测器建模演员与反应者动作间的时序依赖。训练中引入自举上下文编码（BSCE），使用生成的历史而非真实序列进行编码，以缓解自回归生成中的误差累积。进一步提出离线版本ReMFlow，其在离线方法中达到最快推理速度并取得最先进性能。ARMFlow通过全局上下文编码增强语义对齐，单步推理实现高精度与低延迟，并借助BSCE减少误差积累。其单步在线生成在InterHuman和InterX数据集上相比现有在线方法FID降低约30%，尽管仅使用部分序列条件，仍达到离线最优水平。
原文摘要 · Abstract (English)
3D human reaction generation faces three main challenges:(1) high motion fidelity, (2) real-time inference, and (3) autoregressive adaptability for online scenarios. Existing methods fail to meet all three simultaneously. We propose ARMFlow, a MeanFlow-based autoregressive framework that models temporal dependencies between actor and reactor motions. It consists of a causal context encoder and an MLP-based velocity predictor. We introduce Bootstrap Contextual Encoding (BSCE) in training, encoding generated history instead of the ground-truth ones, to alleviate error accumulation in autoregressive generation. We further introduce the offline variant ReMFlow, achieving state-of-the-art performance with the fastest inference among offline methods. Our ARMFlow addresses key limitations of online settings by: (1) enhancing semantic alignment via a global contextual encoder; (2) achieving high accuracy and low latency in a single-step inference; and (3) reducing accumulated errors through BSCE. Our single-step online generation surpasses existing online methods on InterHuman and InterX by about 30% in FID, while matching offline state-of-the-art performance despite using only partial sequence conditions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。