We present Video Motion Graphs, a system designed to generate realistic human motion videos. Using a reference video and conditional signals such as music or motion tags, the system synthesizes new videos by first retrieving video clips with gestures matching the conditions and then generating interpolation frames to seamlessly connect clip boundaries. The core of our approach is HMInterp, a robust Video Frame Interpolation (VFI) model that enables seamless interpolation of discontinuous frames, even for complex motion scenarios like dancing. HMInterp i) employs a dual-branch interpolation approach, combining a Motion Diffusion Model for human skeleton motion interpolation with a diffusion-based video frame interpolation model for final frame generation. ii) adopts condition progressive training to effectively leverage identity strong and weak conditions, such as images and pose. These designs ensure both high video texture quality and accurate motion trajectory. Results show that our Video Motion Graphs outperforms existing generative- and retrieval-based methods for multi-modal conditioned human motion video generation. Project page can be found atthis https URL
View on arXiv@article{liu2025_2503.20218,
title={ Video Motion Graphs },
author={ Haiyang Liu and Zhan Xu and Fa-Ting Hong and Hsin-Ping Huang and Yi Zhou and Yang Zhou },
journal={arXiv preprint arXiv:2503.20218},
year={ 2025 }
}