FlowC2S: Flowing from Current to Succeeding Frames for Fast and Memory-Efficient Video Continuation 事件

FlowC2S: Flowing from Current to Succeeding Frames for Fast and Memory-Efficient Video Continuation arXiv:2604.17625v2 Announce Type: replace Abstract: This paper introduces a novel methodology for generating fast and memory-efficient video continuations. Our method, dubbed FlowC2S, fine-tunes a pre-trained text-to-video flow model to learn a vector field between the current and succeeding video chunks. Two design choices are key. First, we introduce inherent optimal couplings, utilizing tempor