Steady-Forcing: 长时程自然视频扩散中空间持久性与运动连续性的平衡
Steady-Forcing: Balancing Spatial Persistence and Motion Continuity in Long-Horizon Nature Video Diffusion
AI总结：
提出Steady-Forcing框架，通过视觉锚点、运动记忆和蒸馏等技术，在长时程固定相机自然视频生成中平衡背景稳定与运动连续性，优于现有方法。
摘要：
自回归视频扩散模型支持流式生成，但在长时程生成中常退化：静态场景布局漂移，而改善空间稳定性的机制往往抑制运动，导致水流、火焰或烟雾等自然流动停滞。我们研究了固定相机长时程自然视频生成中的这种稳定性-运动权衡，其中两种失败模式比移动相机设置更易区分。我们提出Steady-Forcing，一种结合持久视觉锚点（V-Sink）、指数移动平均运动记忆（EMA-Sink）、块相对时间编码、周期性缓存净化以及从Wan2.1-14B教师模型蒸馏（在任务聚焦配置下使用运动奖励先验）的记忆与训练框架。这些组件共同设计用于在数分钟的自回归生成中保持背景一致性，同时维持视觉上合理的流体动力学。在七个基线上的评估表明，Steady-Forcing改善了长时程背景一致性和成像质量，而盲用户研究显示更强的感知稳定性和运动连续性。基准评估进一步表明，通用的VBench聚合分数对固定相机伪影惩罚不足，同时将漂移引起的光流奖励为动态程度，而不直接惩罚纹理硬化或流动停滞——这激励了未来针对静态相机自然流动评估的任务特定基准。项目页面：https://minar09.github.io/steadyforcing/
英文摘要：
Autoregressive video diffusion models enable streaming generation but often degrade over long rollouts: static scene layouts drift, while mechanisms that improve spatial stability tend to suppress motion, causing natural flows such as water, fire, or smoke to stagnate. We study this stability-motion trade-off in fixed-camera long-horizon nature video generation, where the two failure modes can be more clearly separated than in moving-camera settings. We propose Steady-Forcing, a memory and training framework combining a persistent visual anchor (V-Sink), an exponential moving-average motion memory (EMA-Sink), block-relative temporal encoding, periodic cache purification, and distillation from a Wan2.1-14B teacher with motion-rewarded priors under task-focused configurations. Together, these components are designed to preserve background identity while sustaining visually plausible fluid dynamics over multi-minute autoregressive rollouts. Evaluations across seven baselines show that Steady-Forcing improves long horizon background consistency and imaging quality, while a blind user study indicates stronger perceived stability and motion continuity. The benchmark evaluation further suggest that generic VBench aggregate scores under-penalize fixed-camera artifacts as well as rewarding drift-induced optical flow as Dynamic Degree while not directly penalizing texture hardening or flow stagnation - motivating future task-specific benchmarks for static-camera nature-flow evaluation. Project page: https://minar09.github.io/steadyforcing/
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。
