通过几何原型提升3D点云零样本分割性能，缩小语义与视觉差距。
3D-PointZshotS: Geometry-Aware 3D Point Cloud Zero-Shot Semantic Segmentation Narrowing the Visual-Semantic Gap
- 引入潜伏几何原型增强语义特征的几何细节。
- 在三个数据集上实现最高谐波平均交并比，优于四个基线方法。
- 适合关注零样本3D理解与跨域泛化的研究者。
现有零样本3D点云分割方法在从已见类别到未见类别的迁移，以及语义空间与视觉空间之间存在局限性。为此，本文提出3D-PointZshotS，一种基于几何感知的零样本分割框架，通过潜伏几何原型（LGPs）提升特征生成与对齐能力。具体地，利用交叉注意力机制将LGPs融入生成器，丰富语义特征中的细粒度几何信息；为增强稳定性和泛化能力，设计自一致性损失，使特征对点级扰动保持鲁棒性；此外，重新表征视觉与语义特征于共享空间，弥合语义-视觉鸿沟，促进未见类别的知识迁移。在ScanNet、SemanticKITTI和S3DIS三个真实世界数据集上的实验表明，该方法在谐波mIoU指标上优于四个基线方法。代码已开源。
原文摘要 · Abstract (English)
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}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。