Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model
METADATA ONLY
Loading...
Author / Creator
Date
2025
Publication Type
Conference Paper
ETH Bibliography
yes
METADATA ONLY
Data
Rights / License
Abstract
Generalized few-shot 3D point cloud segmentation (GFS-PCS) adapts models to new classes with few support samples while retaining base class segmentation. Existing GFS-PCS methods enhance prototypes via interacting with support or query features but remain limited by sparse knowledge from few-shot samples. Meanwhile, 3D vision-language models (3D VLMs), generalizing across open-world novel classes, contain rich but noisy novel class knowledge. In this work, we introduce a GFS-PCS framework that synergizes dense but noisy pseudo-labels from 3D VLMs with precise yet sparse few-shot samples to maximize the strengths of both, named GFS-VL. Specifically, we present a prototype-guided pseudo-label selection to filter low-quality regions, followed by an adaptive infilling strategy that combines knowledge from pseudo-label contexts and few-shot samples to adaptively label the filtered, unlabeled areas. Additionally, we design a novel-base mix strategy to embed few-shot samples into training scenes, preserving essential context for improved novel class learning. Moreover, recognizing the limited diversity in current GFS-PCS benchmarks, we introduce two challenging benchmarks with diverse novel classes for comprehensive generalization evaluation. Experiments validate the effectiveness of our framework across models and datasets. Our approach and benchmarks provide a solid foundation for advancing GFS-PCS in the real world.
Permanent link
Publication status
published
External links
Editor
Book title
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Journal / series
Volume
Pages / Article No.
16997 - 17007
Publisher
IEEE
Event
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025)
Edition / version
Methods
Geographic location
Date collected
Date created
Subject
3D segmentation; 3D point cloud; Few-shot segmentation; Generalized few-shot segmentation; Multimodality; Few-shot point cloud segmentation; Generalized few-shot point cloud segmentation