3D Geometric Shape Assembly via Efficient Point Cloud Matching

TL;DR

This paper introduces PMTR, a novel framework for assembling 3D shapes by establishing local point cloud correspondences efficiently, significantly improving accuracy and computational efficiency over existing methods.

Contribution

The paper proposes Proxy Match Transform (PMT) and PMTR, innovative methods for reliable point cloud matching in 3D shape assembly, with demonstrated superior performance and efficiency.

Findings

Outperforms state-of-the-art methods on the Breaking Bad dataset.

Achieves higher accuracy in shape assembly tasks.

Reduces computational and memory costs significantly.

Abstract

Learning to assemble geometric shapes into a larger target structure is a pivotal task in various practical applications. In this work, we tackle this problem by establishing local correspondences between point clouds of part shapes in both coarse- and fine-levels. To this end, we introduce Proxy Match Transform (PMT), an approximate high-order feature transform layer that enables reliable matching between mating surfaces of parts while incurring low costs in memory and computation. Building upon PMT, we introduce a new framework, dubbed Proxy Match TransformeR (PMTR), for the geometric assembly task. We evaluate the proposed PMTR on the large-scale 3D geometric shape assembly benchmark dataset of Breaking Bad and demonstrate its superior performance and efficiency compared to state-of-the-art methods. Project page: https://nahyuklee.github.io/pmtr.