SOURCE-LINKED INTELLIGENCE

PART: Learning 3D Part Assembly and Retrieval with Transformers

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

3D assembly is fundamental to modern manufacturing and digital content creation. In this paper, we present PART, a unified transformer-based framework for 3D part retrieval and assembly: given a target shape and a part library, PART automatically selects the appropriate parts and predicts their 6-DoF poses to reconstruct the target. While prior work has achieved impressive progress on assembling a pre-defined set of parts, this more practical retrieval-based setting remains largely unexplored. The task faces three key challenges: (i) a combinatorially explosive search space that grows exponent

Read original source ↗ Open in workspace

recordType

paper

region

Global