English

Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing

Computer Vision and Pattern Recognition 2024-03-28 v3

Abstract

Generative 3D part assembly involves understanding part relationships and predicting their 6-DoF poses for assembling a realistic 3D shape. Prior work often focus on the geometry of individual parts, neglecting part-whole hierarchies of objects. Leveraging two key observations: 1) super-part poses provide strong hints about part poses, and 2) predicting super-part poses is easier due to fewer superparts, we propose a part-whole-hierarchy message passing network for efficient 3D part assembly. We first introduce super-parts by grouping geometrically similar parts without any semantic labels. Then we employ a part-whole hierarchical encoder, wherein a super-part encoder predicts latent super-part poses based on input parts. Subsequently, we transform the point cloud using the latent poses, feeding it to the part encoder for aggregating super-part information and reasoning about part relationships to predict all part poses. In training, only ground-truth part poses are required. During inference, the predicted latent poses of super-parts enhance interpretability. Experimental results on the PartNet dataset show that our method achieves state-of-the-art performance in part and connectivity accuracy and enables an interpretable hierarchical part assembly. Code is available at https://github.com/pkudba/3DHPA.

Keywords

Cite

@article{arxiv.2402.17464,
  title  = {Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing},
  author = {Bi'an Du and Xiang Gao and Wei Hu and Renjie Liao},
  journal= {arXiv preprint arXiv:2402.17464},
  year   = {2024}
}
R2 v1 2026-06-28T15:01:51.899Z