Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labels

TL;DR

This paper introduces a weakly supervised method for 3D point cloud segmentation that uses significantly fewer labels, leveraging gradient approximation and smoothness constraints to achieve near or better results than fully supervised methods.

Contribution

The paper presents a novel weakly supervised segmentation approach that drastically reduces label requirements while maintaining high accuracy, using gradient approximation and spatial-color smoothness.

Findings

Achieves comparable or better results than fully supervised methods with 10x fewer labels.

Effective on multiple public datasets with varying degrees of supervision.

Demonstrates practical feasibility of low-label point cloud segmentation.

Abstract

Point cloud analysis has received much attention recently; and segmentation is one of the most important tasks. The success of existing approaches is attributed to deep network design and large amount of labelled training data, where the latter is assumed to be always available. However, obtaining 3d point cloud segmentation labels is often very costly in practice. In this work, we propose a weakly supervised point cloud segmentation approach which requires only a tiny fraction of points to be labelled in the training stage. This is made possible by learning gradient approximation and exploitation of additional spatial and color smoothness constraints. Experiments are done on three public datasets with different degrees of weak supervision. In particular, our proposed method can produce results that are close to and sometimes even better than its fully supervised counterpart with 10$\times$ fewer labels.