提出稀疏注意力机制，让视频生成更快更准。
SparSTAR: Sparse Attention for SpaceTime AutoRegressive Video Synthesis
- 按块稀疏计算注意力，只处理关键区域。
- 720p视频生成速度提升1.6倍，质量几乎不变。
- 适合需要高效视频生成的科研与工程应用。
InfinityStar通过图像和片段金字塔实现视觉自回归视频生成，但其尺度变化和跨片段上下文导致高层级注意力计算成本高，且从扩散模型或图像自回归模型复用的稀疏模式不可靠。本文提出SparSTAR，一种无需训练的块稀疏注意力方法，针对此场景优化。在每个高成本尺度和注意力头中，SparSTAR基于当前查询与键激活，对连续键块进行评分，保留必要条件上下文，并通过仅前向传播的稀疏路径执行选定块。我们分析了片段内跨尺度一致性、片段边界间模式持续性以及复用覆盖远距离尺度时的质量退化。分析显示，重要键块会随目标尺度动态变化，因此在每个尺度重新计算块选择比复用转移掩码更可靠。在720p文本到视频与图像到视频生成任务中，SparSTAR保持所有标记和细化尺度，实现约1.6倍端到端加速，同时维持VBench和成对输出重建保真度接近稠密InfinityStar。
原文摘要 · Abstract (English)
InfinityStar extends visual autoregressive generation to video through a sequence of image and clip pyramids. Its changing scale and cross-clip context, however, leave late-scale attention costly and make sparse patterns reused from diffusion or image VAR models unreliable. We introduce SparSTAR, a training-free block-sparse attention method tailored to this setting. At each expensive scale and attention head, SparSTAR scores contiguous key blocks from the current query and key activations, retains required conditioning context, and executes the selected blocks through a forward-only sparse path. We analyze cross-scale consistency within a clip, pattern persistence across clip boundaries, and quality degradation as reuse spans increasingly distant scales. Across these analyses, important key blocks shift, showing that recomputing block selection at each target scale is more reliable than reusing a transferred mask. On 720p text-to-video and image-to-video generation, SparSTAR preserves every token and refinement scale while providing about a 1.6x end-to-end speedup and maintaining VBench and paired-output reconstruction fidelity close to dense InfinityStar.
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。