FlowMotion: Training-Free Flow Guidance for Video Motion Transfer

TL;DR

FlowMotion is a training-free framework for video motion transfer that leverages flow-based model predictions to efficiently and flexibly transfer motion patterns between videos, ensuring smooth motion evolution.

Contribution

It introduces flow guidance and velocity regularization to improve efficiency and stability in training-free video motion transfer using flow-based T2V models.

Findings

Achieves superior efficiency and resource savings.

Provides competitive performance with state-of-the-art methods.

Ensures smooth and stable motion transfer.

Abstract

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.