用语义进度函数分析视频生成的不均衡节奏，实现平滑过渡。
Video Analysis and Generation via a Semantic Progress Function
- 通过语义嵌入距离构建一维语义演化曲线
- 发现生成过程存在语义突变与静止期交替现象
- 可适配各类模型，用于优化生成节奏或分析真实视频
图像和视频生成模型的变换常呈高度非线性：长时间内容几乎不变后突然发生剧烈语义跳跃。为分析并修正此行为，我们提出语义进度函数——一种捕捉序列语义随时间演化的二维表示。对每一帧，计算语义嵌入间的距离，并拟合反映累积语义变化的光滑曲线。该曲线偏离直线的程度揭示了语义节奏的不均。基于此，我们提出语义线性化方法，重新参数化（或重定时）序列，使语义变化以恒定速率展开，从而实现更平滑、连贯的过渡。除线性化外，该框架还提供模型无关的基础，可用于识别时间异常、比较不同生成器的语义节奏，以及将生成或真实视频序列引导至任意目标节奏。
原文摘要 · Abstract (English)
Transformations produced by image and video generation models often evolve in a highly non-linear manner: long stretches where the content barely changes are followed by sudden, abrupt semantic jumps. To analyze and correct this behavior, we introduce a Semantic Progress Function, a one-dimensional representation that captures how the meaning of a given sequence evolves over time. For each frame, we compute distances between semantic embeddings and fit a smooth curve that reflects the cumulative semantic shift across the sequence. Departures of this curve from a straight line reveal uneven semantic pacing. Building on this insight, we propose a semantic linearization procedure that reparameterizes (or retimes) the sequence so that semantic change unfolds at a constant rate, yielding smoother and more coherent transitions. Beyond linearization, our framework provides a model-agnostic foundation for identifying temporal irregularities, comparing semantic pacing across different generators, and steering both generated and real-world video sequences toward arbitrary target pacing.
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。