Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancement

TL;DR

This paper introduces a novel query-guided enhancement method that significantly improves few-shot 3D point cloud segmentation by reducing semantic gaps between support prototypes and query features, applicable to any prototype-based model.

Contribution

It proposes a new approach that adaptively aligns support prototypes with query context, enhancing few-shot segmentation performance in 3D point clouds.

Findings

Achieves significant improvements on S3DIS and ScanNet datasets.

Maintains high efficiency while boosting segmentation accuracy.

Method is agnostic to feature extractors, broadening applicability.

Abstract

Although extensive research has been conducted on 3D point cloud segmentation, effectively adapting generic models to novel categories remains a formidable challenge. This paper proposes a novel approach to improve point cloud few-shot segmentation (PC-FSS) models. Unlike existing PC-FSS methods that directly utilize categorical information from support prototypes to recognize novel classes in query samples, our method identifies two critical aspects that substantially enhance model performance by reducing contextual gaps between support prototypes and query features. Specifically, we (1) adapt support background prototypes to match query context while removing extraneous cues that may obscure foreground and background in query samples, and (2) holistically rectify support prototypes under the guidance of query features to emulate the latter having no semantic gap to the query targets. Our proposed designs are agnostic to the feature extractor, rendering them readily applicable to any prototype-based methods. The experimental results on S3DIS and ScanNet demonstrate notable practical benefits, as our approach achieves significant improvements while still maintaining high efficiency. The code for our approach is available at https://github.com/AaronNZH/Boosting-Few-shot-3D-Point-Cloud-Segmentation-via-Query-Guided-Enhancement