测试图像噪声初始化在视频生成中的效果，发现提升不显著。
Does Semantic Noise Initialization Transfer from Images to Videos? A Paired Diagnostic Study
- 用语义噪声初始化替代标准高斯噪声进行视频生成
- 95%置信区间包含零，整体性能与基线持平
- 建议用提示级配对评估和噪声空间诊断
语义噪声初始化在图像扩散模型中被报道可提升鲁棒性和可控性。但其是否适用于文本到视频（T2V）生成仍不明确，因时间耦合可能引入额外自由度和不稳定性。本研究基于冻结的VideoCrafter风格T2V扩散主干和VBench，在100个提示上对比语义噪声初始化与标准高斯噪声。通过提示级配对测试、自助法置信区间及符号翻转置换检验，观察到时间相关维度有微弱正向趋势；然而95%置信区间包含零（p ~ 0.17），整体得分与基线相当。进一步分析噪声空间中的扰动模式，发现信号较弱或不稳定。研究建议将提示级配对评估和噪声空间诊断作为研究T2V扩散初始化方案的标准实践。
原文摘要 · Abstract (English)
Semantic noise initialization has been reported to improve robustness and controllability in image diffusion models. Whether these gains transfer to text-to-video (T2V) generation remains unclear, since temporal coupling can introduce extra degrees of freedom and instability. We benchmark semantic noise initialization against standard Gaussian noise using a frozen VideoCrafter-style T2V diffusion backbone and VBench on 100 prompts. Using prompt-level paired tests with bootstrap confidence intervals and a sign-flip permutation test, we observe a small positive trend on temporal-related dimensions; however, the 95 percent confidence interval includes zero (p ~ 0.17) and the overall score remains on par with the baseline. To understand this outcome, we analyze the induced perturbations in noise space and find patterns consistent with weak or unstable signal. We recommend prompt-level paired evaluation and noise-space diagnostics as standard practice when studying initialization schemes for T2V diffusion.
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。