3D-PointZshotS: Geometry-Aware 3D Point Cloud Zero-Shot Semantic Segmentation Narrowing the Visual-Semantic Gap

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Minmin, Ren, Huantao, Velipasalar, Senem
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917987525591040
author Yang, Minmin
Ren, Huantao
Velipasalar, Senem
author_facet Yang, Minmin
Ren, Huantao
Velipasalar, Senem
contents Existing zero-shot 3D point cloud segmentation methods often struggle with limited transferability from seen classes to unseen classes and from semantic to visual space. To alleviate this, we introduce 3D-PointZshotS, a geometry-aware zero-shot segmentation framework that enhances both feature generation and alignment using latent geometric prototypes (LGPs). Specifically, we integrate LGPs into a generator via a cross-attention mechanism, enriching semantic features with fine-grained geometric details. To further enhance stability and generalization, we introduce a self-consistency loss, which enforces feature robustness against point-wise perturbations. Additionally, we re-represent visual and semantic features in a shared space, bridging the semantic-visual gap and facilitating knowledge transfer to unseen classes. Experiments on three real-world datasets, namely ScanNet, SemanticKITTI, and S3DIS, demonstrate that our method achieves superior performance over four baselines in terms of harmonic mIoU. The code is available at \href{https://github.com/LexieYang/3D-PointZshotS}{Github}.
format Preprint
id arxiv_https___arxiv_org_abs_2504_12442
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle 3D-PointZshotS: Geometry-Aware 3D Point Cloud Zero-Shot Semantic Segmentation Narrowing the Visual-Semantic Gap
Yang, Minmin
Ren, Huantao
Velipasalar, Senem
Computer Vision and Pattern Recognition
Existing zero-shot 3D point cloud segmentation methods often struggle with limited transferability from seen classes to unseen classes and from semantic to visual space. To alleviate this, we introduce 3D-PointZshotS, a geometry-aware zero-shot segmentation framework that enhances both feature generation and alignment using latent geometric prototypes (LGPs). Specifically, we integrate LGPs into a generator via a cross-attention mechanism, enriching semantic features with fine-grained geometric details. To further enhance stability and generalization, we introduce a self-consistency loss, which enforces feature robustness against point-wise perturbations. Additionally, we re-represent visual and semantic features in a shared space, bridging the semantic-visual gap and facilitating knowledge transfer to unseen classes. Experiments on three real-world datasets, namely ScanNet, SemanticKITTI, and S3DIS, demonstrate that our method achieves superior performance over four baselines in terms of harmonic mIoU. The code is available at \href{https://github.com/LexieYang/3D-PointZshotS}{Github}.
title 3D-PointZshotS: Geometry-Aware 3D Point Cloud Zero-Shot Semantic Segmentation Narrowing the Visual-Semantic Gap
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.12442