Contrastive Learning for Self-Supervised Pre-Training of Point Cloud Segmentation Networks With Image Data

TL;DR

This paper introduces a self-supervised pre-training method that combines image and point cloud data to improve 3D segmentation with minimal annotations, requiring only a single scan and no localization info.

Contribution

It presents a novel approach that leverages image features to pre-train 3D models, reducing the need for multiple scans and registration in point cloud segmentation tasks.

Findings

Achieves comparable performance to multi-scan methods

Requires only a single scene scan for pre-training

Effectively combines image and point cloud data

Abstract

Reducing the quantity of annotations required for supervised training is vital when labels are scarce and costly. This reduction is particularly important for semantic segmentation tasks involving 3D datasets, which are often significantly smaller and more challenging to annotate than their image-based counterparts. Self-supervised pre-training on unlabelled data is one way to reduce the amount of manual annotations needed. Previous work has focused on pre-training with point clouds exclusively. While useful, this approach often requires two or more registered views. In the present work, we combine image and point cloud modalities by first learning self-supervised image features and then using these features to train a 3D model. By incorporating image data, which is often included in many 3D datasets, our pre-training method only requires a single scan of a scene and can be applied to cases where localization information is unavailable. We demonstrate that our pre-training approach, despite using single scans, achieves comparable performance to other multi-scan, point cloud-only methods.