SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentation

TL;DR

SCOPE introduces a background-guided prototype enrichment framework for incremental 3D segmentation, leveraging background pseudo-instances to improve novel class learning without retraining, achieving state-of-the-art results.

Contribution

It proposes a novel background-guided prototype enrichment method for incremental 3D segmentation that enhances novel class recognition without retraining the backbone.

Findings

Achieves state-of-the-art performance on ScanNet and S3DIS datasets.

Improves novel-class IoU by up to 6.98% and 3.61%.

Maintains low catastrophic forgetting.

Abstract

Incremental Few-Shot (IFS) segmentation aims to learn new categories over time from only a few annotations. Although widely studied in 2D, it remains underexplored for 3D point clouds. Existing methods suffer from catastrophic forgetting or fail to learn discriminative prototypes under sparse supervision, and often overlook a key cue: novel categories frequently appear as unlabelled background in base-training scenes. We introduce SCOPE (Scene-COntextualised Prototype Enrichment), a plug-and-play background-guided prototype enrichment framework that integrates with any prototype-based 3D segmentation method. After base training, a class-agnostic segmentation model extracts high-confidence pseudo-instances from background regions to build a prototype pool. When novel classes arrive with few labelled samples, relevant background prototypes are retrieved and fused with few-shot prototypes to form enriched representations without retraining the backbone or adding parameters. Experiments on ScanNet and S3DIS show that SCOPE achieves SOTA performance, improving novel-class IoU by up to 6.98% and 3.61%, and mean IoU by 2.25% and 1.70%, respectively, while maintaining low forgetting. Code is available https://github.com/Surrey-UP-Lab/SCOPE.