arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.05682cs.CV
收藏

H3DNet:使用混合几何图元的3D目标检测

H3DNet: 3D Object Detection Using Hybrid Geometric Primitives

The University of Texas at Austin(德克萨斯大学奥斯汀分校)

Zaiwei Zhang, Bo Sun, Haitao Yang, Qixing Huang

摘要:

我们引入H3 DNet,它以无色的3D点云作为输入,并输出一组面向对象的边界框(或BB)及其语义标签。H3 DNet的关键思想是预测几何图元的混合集,即,BB中心、BB面中心和BB边中心。我们展示了如何通过定义对象和几何图元之间的距离函数将预测的几何图元转换为对象建议。该距离函数能够持续优化对象建议,其局部最小值提供高保真对象建议。然后,H3 DNet利用匹配和细化模块将对象建议分类为检测到的对象,并微调检测到的对象的几何参数。几何基元的混合集合不仅比使用单一类型的几何基元为目标检测提供更准确的信号,而且还提供了对所得到的3D布局的过完备约束集合。因此,H3 DNet可以容忍预测几何图元中的离群值。我们的模型在两个具有真实3D扫描的大型数据集ScanNet和SUN RGB-D上实现了最先进的3D检测结果。

英文摘要:

We introduce H3DNet, which takes a colorless 3D point cloud as input and outputs a collection of oriented object bounding boxes (or BB) and their semantic labels. The critical idea of H3DNet is to predict a hybrid set of geometric primitives, i.e., BB centers, BB face centers, and BB edge centers. We show how to convert the predicted geometric primitives into object proposals by defining a distance function between an object and the geometric primitives. This distance function enables continuous optimization of object proposals, and its local minimums provide high-fidelity object proposals. H3DNet then utilizes a matching and refinement module to classify object proposals into detected objects and fine-tune the geometric parameters of the detected objects. The hybrid set of geometric primitives not only provides more accurate signals for object detection than using a single type of geometric primitives, but it also provides an overcomplete set of constraints on the resulting 3D layout. Therefore, H3DNet can tolerate outliers in predicted geometric primitives. Our model achieves state-of-the-art 3D detection results on two large datasets with real 3D scans, ScanNet and SUN RGB-D.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑