Drag Anything: Motion Control for Anything Using Entity Representation

Abstract

We introduce , which utilizes a entity representation to achieve motion control for any object in controllable video generation. Comparison to existing motion control methods, offers several advantages. Firstly, trajectory-based is more user-friendly for interaction, when acquiring other guidance signals ( masks, depth maps) is labor-intensive. Users only need to draw a line (trajectory) during interaction. Secondly, our entity representation serves as an open-domain embedding capable of representing any object, enabling the control of motion for diverse entities, including background. Lastly, our entity representation allows simultaneous and distinct motion control for multiple objects. Extensive experiments demonstrate that our achieves state-of-the-art performance for FVD, FID, and User Study, particularly in terms of object motion control, where our method surpasses the previous methods ( DragNUWA) by 26% in human voting. The project website is at: blueDragAnything.

Cite

Text

Wu et al. "Drag Anything: Motion Control for Anything Using Entity Representation." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-72670-5_19

Markdown

[Wu et al. "Drag Anything: Motion Control for Anything Using Entity Representation." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/wu2024eccv-drag/) doi:10.1007/978-3-031-72670-5_19

BibTeX

@inproceedings{wu2024eccv-drag,
  title     = {{Drag Anything: Motion Control for Anything Using Entity Representation}},
  author    = {Wu, Weijia and Li, Zhuang and Gu, Yuchao and Zhao, Rui and He, Yefei and Zhang, David Junhao and Shou, Mike Zheng and Li, Yan and Gao, Tingting and Di, Zhang},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2024},
  doi       = {10.1007/978-3-031-72670-5_19},
  url       = {https://mlanthology.org/eccv/2024/wu2024eccv-drag/}
}