无需训练即可无限生成视频，保持长期一致性与流畅运动
MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens
- 用动态记忆令牌压缩历史信息，分长短时流维持身份与动作
- 在线位置编码避免位置冲突，实现无偏差的时序聚合
- 适合需要长时一致性的视频生成场景，如影视创作
自回归扩散模型支持实时帧流输出，但现有滑动窗口缓存会丢弃过往上下文，导致长时间生成时出现画质下降、主体漂移和运动停滞。当前方法通过固定早期标记作为注意力锚点来保留上下文，但静态锚点无法反映不断变化的视频内容。本文提出MemRoPE，一种无需训练的框架，包含两个协同设计组件：记忆令牌通过指数移动平均持续将历史键值压缩为长短时双流，以在固定大小缓存中同时保持全局身份与近期动态；在线RoPE索引缓存未旋转的键，并在注意力计算时动态应用位置嵌入，确保聚合过程无位置相位冲突。这两个机制相互促进：位置解耦使时序聚合定义清晰，而聚合使得固定大小缓存可支持无限生成。大量实验表明，MemRoPE在分钟至小时级生成中显著优于现有方法，在时间连贯性、视觉保真度和主体一致性方面表现更优。
原文摘要 · Abstract (English)
Autoregressive diffusion enables real-time frame streaming, yet existing sliding-window caches discard past context, causing fidelity degradation, identity drift, and motion stagnation over long horizons. Current approaches preserve a fixed set of early tokens as attention sinks, but this static anchor cannot reflect the evolving content of a growing video. We introduce MemRoPE, a training-free framework with two co-designed components. Memory Tokens continuously compress all past keys into dual long-term and short-term streams via exponential moving averages, maintaining both global identity and recent dynamics within a fixed-size cache. Online RoPE Indexing caches unrotated keys and applies positional embeddings dynamically at attention time, ensuring the aggregation is free of conflicting positional phases. These two mechanisms are mutually enabling: positional decoupling makes temporal aggregation well-defined, while aggregation makes fixed-size caching viable for unbounded generation. Extensive experiments validate that MemRoPE outperforms existing methods in temporal coherence, visual fidelity, and subject consistency across minute- to hour-scale generation.
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。