FlowMotion: Training-Free Flow Guidance for Video Motion Transfer
This addresses the need for efficient and flexible motion transfer in video generation, though it is incremental as it builds on existing flow-based T2V models.
The paper tackles the problem of video motion transfer by proposing FlowMotion, a training-free framework that uses flow guidance from latent predictions to align motion patterns, achieving competitive performance with improved efficiency.
Video motion transfer aims to generate a target video that inherits motion patterns from a source video while rendering new scenes. Existing training-free approaches focus on constructing motion guidance based on the intermediate outputs of pre-trained T2V models, which results in heavy computational overhead and limited flexibility. In this paper, we present FlowMotion, a novel training-free framework that enables efficient and flexible motion transfer by directly leveraging the predicted outputs of flow-based T2V models. Our key insight is that early latent predictions inherently encode rich temporal information. Motivated by this, we propose flow guidance, which extracts motion representations based on latent predictions to align motion patterns between source and generated videos. We further introduce a velocity regularization strategy to stabilize optimization and ensure smooth motion evolution. By operating purely on model predictions, FlowMotion achieves superior time and resource efficiency as well as competitive performance compared with state-of-the-art methods.