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

arXiv:2402.17464v1 Announce Type: new
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 …

abstract arxiv assembly cs.cv focus generative geometry key objects part prior relationships type understanding via work