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_10Markdown
[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_10BibTeX
@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/}
}