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

TL;DR

This paper introduces a hierarchical message passing network for 3D part assembly that leverages super-part relationships to improve pose prediction accuracy and interpretability in complex object assemblies.

Contribution

It proposes a novel part-whole hierarchy approach that groups parts into super-parts and uses their predicted poses to enhance part pose estimation, outperforming prior methods.

Findings

Achieves state-of-the-art accuracy on PartNet dataset.

Provides interpretable hierarchical assembly process.

Demonstrates improved connectivity prediction.

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.