Rolling Diffusion Models
CoRR(2024)
摘要
Diffusion models have recently been increasingly applied to temporal data
such as video, fluid mechanics simulations, or climate data. These methods
generally treat subsequent frames equally regarding the amount of noise in the
diffusion process. This paper explores Rolling Diffusion: a new approach that
uses a sliding window denoising process. It ensures that the diffusion process
progressively corrupts through time by assigning more noise to frames that
appear later in a sequence, reflecting greater uncertainty about the future as
the generation process unfolds. Empirically, we show that when the temporal
dynamics are complex, Rolling Diffusion is superior to standard diffusion. In
particular, this result is demonstrated in a video prediction task using the
Kinetics-600 video dataset and in a chaotic fluid dynamics forecasting
experiment.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要