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{this https URL}{Github}.
View on arXiv@article{yang2025_2504.12442,
title={ 3D-PointZshotS: Geometry-Aware 3D Point Cloud Zero-Shot Semantic Segmentation Narrowing the Visual-Semantic Gap },
author={ Minmin Yang and Huantao Ren and Senem Velipasalar },
journal={arXiv preprint arXiv:2504.12442},
year={ 2025 }
}