HiAR：通过分层去噪实现高效的自回归长视频生成
HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising
AI总结：
HiAR通过分层去噪框架在保持时间连续性的同时减少误差传播，实现高效长视频生成。
摘要：
自回归（AR）扩散提供了一个有前景的框架，用于生成理论上无限长的视频。然而，一个主要挑战是保持时间连续性的同时防止因误差累积导致的逐步质量下降。为确保连续性，现有方法通常条件于高度去噪的上下文；然而，这种做法会以高确定性传播预测误差，从而加剧降级。在本文中，我们主张高度干净的上下文是不必要的。受双向扩散模型的启发，该模型在共享噪声水平上去噪帧同时保持连贯性，我们提出条件于当前块相同噪声水平的上下文可以为时间一致性提供足够的信号，同时有效缓解误差传播。基于这一见解，我们提出了HiAR，一种分层去噪框架，反转了传统的生成顺序：而不是依次完成每个块，它在每次去噪步骤中对所有块进行因果生成，使得每个块始终被相同噪声水平的上下文所条件。这种分层结构自然允许流水线并行推理，使我们的4步设置中实现了1.8倍的时钟时间加速。我们进一步发现，在这种范式下，自我回滚蒸馏会放大模式寻求反KL目标固有的低运动捷径。为应对这一问题，我们引入了双向注意力模式下的前向KL正则化器，该正则化器在因果推理中保持运动多样性，而不会干扰蒸馏损失。在VBench（20秒生成）上，HiAR在所有比较方法中取得了最佳总体分数和最低的时间漂移。
英文摘要：
Autoregressive (AR) diffusion offers a promising framework for generating videos of theoretically infinite length. However, a major challenge is maintaining temporal continuity while preventing the progressive quality degradation caused by error accumulation. To ensure continuity, existing methods typically condition on highly denoised contexts; yet, this practice propagates prediction errors with high certainty, thereby exacerbating degradation. In this paper, we argue that a highly clean context is unnecessary. Drawing inspiration from bidirectional diffusion models, which denoise frames at a shared noise level while maintaining coherence, we propose that conditioning on context at the same noise level as the current block provides sufficient signal for temporal consistency while effectively mitigating error propagation. Building on this insight, we propose HiAR, a hierarchical denoising framework that reverses the conventional generation order: instead of completing each block sequentially, it performs causal generation across all blocks at every denoising step, so that each block is always conditioned on context at the same noise level. This hierarchy naturally admits pipelined parallel inference, yielding a 1.8 wall-clock speedup in our 4-step setting. We further observe that self-rollout distillation under this paradigm amplifies a low-motion shortcut inherent to the mode-seeking reverse-KL objective. To counteract this, we introduce a forward-KL regulariser in bidirectional-attention mode, which preserves motion diversity for causal inference without interfering with the distillation loss. On VBench (20s generation), HiAR achieves the best overall score and the lowest temporal drift among all compared methods.
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。
