Open-world Point Cloud Semantic Segmentation: A Human-in-the-loop Framework

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Peng, Yang, Songru, Sun, Jinsheng, Li, Weiqing, Su, Zhiyong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908480877625344
author Zhang, Peng
Yang, Songru
Sun, Jinsheng
Li, Weiqing
Su, Zhiyong
author_facet Zhang, Peng
Yang, Songru
Sun, Jinsheng
Li, Weiqing
Su, Zhiyong
contents Open-world point cloud semantic segmentation (OW-Seg) aims to predict point labels of both base and novel classes in real-world scenarios. However, existing methods rely on resource-intensive offline incremental learning or densely annotated support data, limiting their practicality. To address these limitations, we propose HOW-Seg, the first human-in-the-loop framework for OW-Seg. Specifically, we construct class prototypes, the fundamental segmentation units, directly on the query data, avoiding the prototype bias caused by intra-class distribution shifts between the support and query data. By leveraging sparse human annotations as guidance, HOW-Seg enables prototype-based segmentation for both base and novel classes. Considering the lack of granularity of initial prototypes, we introduce a hierarchical prototype disambiguation mechanism to refine ambiguous prototypes, which correspond to annotations of different classes. To further enrich contextual awareness, we employ a dense conditional random field (CRF) upon the refined prototypes to optimize their label assignments. Through iterative human feedback, HOW-Seg dynamically improves its predictions, achieving high-quality segmentation for both base and novel classes. Experiments demonstrate that with sparse annotations (e.g., one-novel-class-one-click), HOW-Seg matches or surpasses the state-of-the-art generalized few-shot segmentation (GFS-Seg) method under the 5-shot setting. When using advanced backbones (e.g., Stratified Transformer) and denser annotations (e.g., 10 clicks per sub-scene), HOW-Seg achieves 85.27% mIoU on S3DIS and 66.37% mIoU on ScanNetv2, significantly outperforming alternatives.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04962
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Open-world Point Cloud Semantic Segmentation: A Human-in-the-loop Framework
Zhang, Peng
Yang, Songru
Sun, Jinsheng
Li, Weiqing
Su, Zhiyong
Computer Vision and Pattern Recognition
Graphics
Open-world point cloud semantic segmentation (OW-Seg) aims to predict point labels of both base and novel classes in real-world scenarios. However, existing methods rely on resource-intensive offline incremental learning or densely annotated support data, limiting their practicality. To address these limitations, we propose HOW-Seg, the first human-in-the-loop framework for OW-Seg. Specifically, we construct class prototypes, the fundamental segmentation units, directly on the query data, avoiding the prototype bias caused by intra-class distribution shifts between the support and query data. By leveraging sparse human annotations as guidance, HOW-Seg enables prototype-based segmentation for both base and novel classes. Considering the lack of granularity of initial prototypes, we introduce a hierarchical prototype disambiguation mechanism to refine ambiguous prototypes, which correspond to annotations of different classes. To further enrich contextual awareness, we employ a dense conditional random field (CRF) upon the refined prototypes to optimize their label assignments. Through iterative human feedback, HOW-Seg dynamically improves its predictions, achieving high-quality segmentation for both base and novel classes. Experiments demonstrate that with sparse annotations (e.g., one-novel-class-one-click), HOW-Seg matches or surpasses the state-of-the-art generalized few-shot segmentation (GFS-Seg) method under the 5-shot setting. When using advanced backbones (e.g., Stratified Transformer) and denser annotations (e.g., 10 clicks per sub-scene), HOW-Seg achieves 85.27% mIoU on S3DIS and 66.37% mIoU on ScanNetv2, significantly outperforming alternatives.
title Open-world Point Cloud Semantic Segmentation: A Human-in-the-loop Framework
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2508.04962