Semi-supervised 3D shape segmentation with multilevel consistency and part substitution

TL;DR

This paper introduces a semi-supervised approach for 3D shape segmentation that leverages multilevel consistency and part substitution to improve learning from limited labeled data and abundant unlabeled data.

Contribution

It proposes a novel multilevel consistency loss and a part substitution scheme to enhance semi-supervised 3D segmentation performance.

Findings

Outperforms existing semi-supervised methods on PartNet and ShapeNetPart

Achieves superior results on indoor scene segmentation on ScanNet

Demonstrates effectiveness of multilevel consistency and part substitution

Abstract

The lack of fine-grained 3D shape segmentation data is the main obstacle to developing learning-based 3D segmentation techniques. We propose an effective semi-supervised method for learning 3D segmentations from a few labeled 3D shapes and a large amount of unlabeled 3D data. For the unlabeled data, we present a novel multilevel consistency loss to enforce consistency of network predictions between perturbed copies of a 3D shape at multiple levels: point-level, part-level, and hierarchical level. For the labeled data, we develop a simple yet effective part substitution scheme to augment the labeled 3D shapes with more structural variations to enhance training. Our method has been extensively validated on the task of 3D object semantic segmentation on PartNet and ShapeNetPart, and indoor scene semantic segmentation on ScanNet. It exhibits superior performance to existing semi-supervised and unsupervised pre-training 3D approaches. Our code and trained models are publicly available at https://github.com/isunchy/semi_supervised_3d_segmentation.