不训练即可融合几何与语义信息，提升点云识别准确率
Training-Free Point Cloud Recognition Based on Geometric and Semantic Information Fusion
- 不依赖训练，通过非参数化提取几何特征，结合文本对齐模型获取语义特征
- 在ModelNet和ScanObjectNN上优于现有最先进方法，少样本场景下性能更优
- 适合资源受限或需快速部署的点云识别场景
由于显著降低计算资源和时间成本，无需训练的点云识别方法日益流行。然而，现有方法通常仅提取几何或语义特征，存在局限性。本文首次提出一种融合几何与语义信息的新型无训练方法。几何分支采用非参数策略提取特征，语义分支则利用与文本特征对齐的模型获取语义特征。此外，引入GFE模块补全点云几何信息，MFF模块增强少样本设置下的性能。实验结果表明，该方法在ModelNet和ScanObjectNN等主流基准数据集上超越现有最先进的无训练方法。
原文摘要 · Abstract (English)
The trend of employing training-free methods for point cloud recognition is becoming increasingly popular due to its significant reduction in computational resources and time costs. However, existing approaches are limited as they typically extract either geometric or semantic features. To address this limitation, we are the first to propose a novel training-free method that integrates both geometric and semantic features. For the geometric branch, we adopt a non-parametric strategy to extract geometric features. In the semantic branch, we leverage a model aligned with text features to obtain semantic features. Additionally, we introduce the GFE module to complement the geometric information of point clouds and the MFF module to improve performance in few-shot settings. Experimental results demonstrate that our method outperforms existing state-of-the-art training-free approaches on mainstream benchmark datasets, including ModelNet and ScanObiectNN.
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。