Performances on standard 3D point cloud benchmarks have plateaued, resulting in oversized models and complex network design to make a fractional improvement. We present an alternative to enhance existing deep neural networks without any redesigning or extra parameters, termed as Spatial-Neighbor Adapter (SN-Adapter). Building on any trained 3D network, we utilize its learned encoding capability to extract features of the training dataset and summarize them as prototypical spatial knowledge. For a test point cloud, the SN-Adapter retrieves k nearest neighbors (k-NN) from the pre-constructed spatial prototypes and linearly interpolates the k-NN prediction with that of the original 3D network. By providing complementary characteristics, the proposed SN-Adapter serves as a plug-and-play module to economically improve performance in a non-parametric manner. More importantly, our SN-Adapter can be effectively generalized to various 3D tasks, including shape classification, part segmentation, and 3D object detection, demonstrating its superiority and robustness. We hope our approach could show a new perspective for point cloud analysis and facilitate future research.
翻译:标准 3D 点云基准的性能已经稳定下来,导致超大模型和复杂的网络设计达到分数改进。我们提出了一种替代方法,可以加强现有的深神经网络,而不进行重新设计或增加参数,称为空间邻里适应器(SN-Adapter),在任何经过培训的3D网络的基础上,我们利用其所学的编码能力提取培训数据集的特征,并把它们归纳为原型空间知识。对于试验点云来说,SN-Adapter从预构的空间原型中检索到 k最近的邻里(k-NNN),并且用原3D网络的特性将 k-NN预测线性地插入。通过提供互补特征,拟议的SN-Adapter作为一个插座模块,以非参数的方式从经济上改善性能。更重要的是,我们的SN-Adapter可以有效地推广到各种3D任务,包括形状分类、部分分解和3D 对象探测,表明其优越性和坚固性。我们希望我们的方法能够展示点分析的新观点,并便利未来的研究。</s>