通过对角蒸馏实现流式自回归视频生成
Streaming Autoregressive Video Generation via Diagonal Distillation
AI总结：
本文提出对角蒸馏方法，通过不对称生成策略和隐式光学流建模，在减少计算步骤的同时提升视频生成的运动质量和效率。
摘要：
大规模预训练扩散模型显著提升了生成视频的质量，但其在实时流媒体中的应用仍受到限制。自回归模型为顺序帧合成提供了自然的框架，但实现高保真度需要大量计算。扩散蒸馏可以将这些模型压缩成高效的少步变体，但现有的视频蒸馏方法大多采用图像特定的方法，忽略了时间依赖性。这些技术在图像生成方面表现优异，但在视频合成中表现不佳，表现出减少的运动一致性、长序列中的误差累积以及延迟与质量的权衡。我们识别出导致这些限制的两个因素：在步骤减少过程中对时间上下文利用不足以及在下一区块预测中隐式预测后续噪声水平（即暴露偏差）。为了解决这些问题，我们提出了对角蒸馏，它与现有方法正交，并更好地利用视频块和去噪步骤之间的时间信息。我们的方法的核心是一种不对称的生成策略：早期更多步骤，后期更少步骤。这种设计使后期块可以从充分处理的早期块中继承丰富的外观信息，同时使用部分去噪的块作为后续合成的条件输入。通过在块生成过程中对后续噪声水平的隐式预测与实际推理条件对齐，我们的方法缓解了误差传播并减少了长范围序列中的过饱和。我们进一步引入隐式光学流建模以在严格步骤约束下保持运动质量。我们的方法在2.61秒内生成5秒视频（最高31 FPS），比未蒸馏模型快了277.3倍。
英文摘要：
Large pretrained diffusion models have significantly enhanced the quality of generated videos, and yet their use in real-time streaming remains limited. Autoregressive models offer a natural framework for sequential frame synthesis but require heavy computation to achieve high fidelity. Diffusion distillation can compress these models into efficient few-step variants, but existing video distillation approaches largely adapt image-specific methods that neglect temporal dependencies. These techniques often excel in image generation but underperform in video synthesis, exhibiting reduced motion coherence, error accumulation over long sequences, and a latency-quality trade-off. We identify two factors that result in these limitations: insufficient utilization of temporal context during step reduction and implicit prediction of subsequent noise levels in next-chunk prediction (i.e., exposure bias). To address these issues, we propose Diagonal Distillation, which operates orthogonally to existing approaches and better exploits temporal information across both video chunks and denoising steps. Central to our approach is an asymmetric generation strategy: more steps early, fewer steps later. This design allows later chunks to inherit rich appearance information from thoroughly processed early chunks, while using partially denoised chunks as conditional inputs for subsequent synthesis. By aligning the implicit prediction of subsequent noise levels during chunk generation with the actual inference conditions, our approach mitigates error propagation and reduces oversaturation in long-range sequences. We further incorporate implicit optical flow modeling to preserve motion quality under strict step constraints. Our method generates a 5-second video in 2.61 seconds (up to 31 FPS), achieving a 277.3x speedup over the undistilled model.
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。
