DragAPart: Learning a Part-Level Motion Prior for Articulated Objects

Abstract

We introduce , a method that, given an image and a set of drags as input, generates a new image of the same object that responds to the action of the drags. Differently from prior works that focused on repositioning objects, predicts part-level interactions, such as opening and closing a drawer. We study this problem as a proxy for learning a generalist motion model, not restricted to a specific kinematic structure or object category. We start from a pre-trained image generator and fine-tune it on a new synthetic dataset, , which we introduce. Combined with a new encoding for the drags and dataset randomization, the model generalizes well to real images and different categories. Compared to prior motion-controlled generators, we demonstrate much better part-level motion understanding.

Cite

Text

Li et al. "DragAPart: Learning a Part-Level Motion Prior for Articulated Objects." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-72627-9_10

Markdown

[Li et al. "DragAPart: Learning a Part-Level Motion Prior for Articulated Objects." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/li2024eccv-dragapart/) doi:10.1007/978-3-031-72627-9_10

BibTeX

@inproceedings{li2024eccv-dragapart,
  title     = {{DragAPart: Learning a Part-Level Motion Prior for Articulated Objects}},
  author    = {Li, Ruining and Zheng, Chuanxia and Rupprecht, Christian and Vedaldi, Andrea},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2024},
  doi       = {10.1007/978-3-031-72627-9_10},
  url       = {https://mlanthology.org/eccv/2024/li2024eccv-dragapart/}
}