MoTrans: Customized Motion Transfer with Text-driven Video Diffusion Models

TL;DR

MoTrans is a novel method that enables customized motion transfer in video generation by decoupling appearance and motion using multimodal prompts and motion-specific embeddings, outperforming existing approaches.

Contribution

The paper introduces MoTrans, a new approach that effectively models and transfers specific human-centric motions in videos using multimodal prompts and appearance injection.

Findings

Effective motion pattern learning from limited reference videos

Superior performance in customized video generation tasks

Decoupling appearance and motion improves generation quality

Abstract

Existing pretrained text-to-video (T2V) models have demonstrated impressive abilities in generating realistic videos with basic motion or camera movement. However, these models exhibit significant limitations when generating intricate, human-centric motions. Current efforts primarily focus on fine-tuning models on a small set of videos containing a specific motion. They often fail to effectively decouple motion and the appearance in the limited reference videos, thereby weakening the modeling capability of motion patterns. To this end, we propose MoTrans, a customized motion transfer method enabling video generation of similar motion in new context. Specifically, we introduce a multimodal large language model (MLLM)-based recaptioner to expand the initial prompt to focus more on appearance and an appearance injection module to adapt appearance prior from video frames to the motion modeling process. These complementary multimodal representations from recaptioned prompt and video frames promote the modeling of appearance and facilitate the decoupling of appearance and motion. In addition, we devise a motion-specific embedding for further enhancing the modeling of the specific motion. Experimental results demonstrate that our method effectively learns specific motion pattern from singular or multiple reference videos, performing favorably against existing methods in customized video generation.