通过超点聚类增强3D点云边界，实现更清晰的显著物体分割。
Geometry-Aware 3D Salient Object Detection Network
- 用超点聚类显式建模几何结构，提升边界感知能力。
- 在PCSOD数据集上达到新最优性能，显著改善复杂背景下的分割效果。
- 适合做3D场景理解、机器人感知等需要精确物体边界的任务。
点云显著物体检测近年来受到广泛关注。由于现有方法未能充分挖掘3D物体的几何上下文信息，导致在复杂背景下分割时出现边界模糊问题。本文提出一种几何感知的3D显著物体检测网络，通过显式将点聚类为超点来增强物体几何边界，从而实现具有清晰边界的完整物体分割。具体而言，我们首先设计了一个简单而有效的超点划分模块，用于将点划分为超点；为进一步提升超点质量，提出了无类别依赖的点云损失函数，以学习区分性点特征，辅助超点聚类。获得超点后，我们引入几何增强模块，利用超点-点注意力机制将几何信息聚合到点特征中，进而预测出边界清晰的显著图。大量实验表明，本方法在PCSOD数据集上达到新的最先进水平。
原文摘要 · Abstract (English)
Point cloud salient object detection has attracted the attention of researchers in recent years. Since existing works do not fully utilize the geometry context of 3D objects, blurry boundaries are generated when segmenting objects with complex backgrounds. In this paper, we propose a geometry-aware 3D salient object detection network that explicitly clusters points into superpoints to enhance the geometric boundaries of objects, thereby segmenting complete objects with clear boundaries. Specifically, we first propose a simple yet effective superpoint partition module to cluster points into superpoints. In order to improve the quality of superpoints, we present a point cloud class-agnostic loss to learn discriminative point features for clustering superpoints from the object. After obtaining superpoints, we then propose a geometry enhancement module that utilizes superpoint-point attention to aggregate geometric information into point features for predicting the salient map of the object with clear boundaries. Extensive experiments show that our method achieves new state-of-the-art performance on the PCSOD dataset.
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。