Towards realistic symmetry-based completion of previously unseen point clouds

TL;DR

This paper introduces a symmetry-based, training-free point cloud completion framework that effectively repairs damaged 3D scans of unseen objects, especially symmetric ones, outperforming existing methods in real-world scenarios.

Contribution

A novel symmetry-based completion framework that does not require training data, specifically designed for real-world, unseen object scans with damages.

Findings

Achieves state-of-the-art efficiency on real-world customer scans.

Performs well on symmetric objects common in man-made environments.

Outperforms existing methods on benchmark datasets.

Abstract

3D scanning is a complex multistage process that generates a point cloud of an object typically containing damaged parts due to occlusions, reflections, shadows, scanner motion, specific properties of the object surface, imperfect reconstruction algorithms, etc. Point cloud completion is specifically designed to fill in the missing parts of the object and obtain its high-quality 3D representation. The existing completion approaches perform well on the academic datasets with a predefined set of object classes and very specific types of defects; however, their performance drops significantly in the real-world settings and degrades even further on previously unseen object classes. We propose a novel framework that performs well on symmetric objects, which are ubiquitous in man-made environments. Unlike learning-based approaches, the proposed framework does not require training data and is capable of completing non-critical damages occurring in customer 3D scanning process using e.g. Kinect, time-of-flight, or structured light scanners. With thorough experiments, we demonstrate that the proposed framework achieves state-of-the-art efficiency in point cloud completion of real-world customer scans. We benchmark the framework performance on two types of datasets: properly augmented existing academic dataset and the actual 3D scans of various objects.