InterCMDM：用于自回归人体交互生成的块因果扩散
InterCMDM: Block-Causal Diffusion for Autoregressive Human Interaction Generation
AI总结：
提出InterCMDM块因果潜扩散框架，通过双流因果扩散Transformer和多重任务注意力掩码实现自回归双人交互生成，解决因果性缺失和时间漂移问题，在InterHuman和InterX上达到最优性能。
摘要：
文本条件的人体交互生成必须捕捉个体内部的长程时间因果性以及伙伴之间的紧密协调耦合。现有的交互扩散模型通常使用双向注意力对完整序列进行去噪，这模糊了因果性并阻碍了流式和长程生成。自回归替代方法强制因果性，但常常遭受时间漂移，导致协调退化和随时间的不稳定交互动态。我们提出InterCMDM，一种用于自回归双人交互生成的块因果潜扩散框架。InterCMDM引入了一个双流因果扩散Transformer，为每个人维护独立的因果流，同时通过具有多重任务注意力掩码的统一双流注意力来建模人际依赖。这些掩码在单一注意力机制内统一了交互建模，并支持多种协调行为，包括同时动作、反应性响应、领导-跟随动态和独立运动。通过在这些掩码配置上训练单一模型作为数据增强的一种形式，InterCMDM通过在推理时简单地选择所需的注意力掩码来实现可控的交互生成。最后，块状扩散目标使得能够在长序列上稳定地潜变量展开，无需重复的解码-编码循环。InterCMDM在InterHuman和Inter-X上达到了最先进的性能，改善了文本-运动对齐、真实感和长程连续性。
英文摘要：
Text-conditioned human interaction generation must capture both long-range temporal causality within each individual and tightly coupled coordination between partners. Existing interaction diffusion models typically denoise full sequences using bidirectional attention, which obscures causality and hinders streaming and long-horizon generation. Autoregressive alternatives enforce causality but often suffer from temporal drift, leading to coordination degradation and unstable interaction dynamics over time. We propose InterCMDM, a block-causal latent diffusion framework for autoregressive two-person interaction generation. InterCMDM introduces a Dual-Stream Causal Diffusion Transformer that maintains separate causal streams for each person while modeling inter-person dependencies via unified dual-stream attention with multi-task attention masks. These masks unify interaction modeling within a single attention mechanism and support diverse coordination behaviors, including simultaneous actions, reactive responses, leader-follower dynamics, and independent motion. By training a single model across these mask configurations as a form of data augmentation, InterCMDM enables controllable interaction generation by simply selecting the desired attention mask at inference time. Finally, a block-wise diffusion objective enables stable latent rollout over long sequences without repeated decode-encode cycles. InterCMDM achieves state-of-the-art performance on InterHuman and Inter-X, improving text-motion alignment, realism, and long-horizon continuity.
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。
