「图像处理」用于三维物体检测的三维骨干网络

用于三维物体检测的三维骨干网络

题目：

3D Backbone Network for 3D Object Detection

作者：

Xuesong Li，Jose E Guivant，Ngaiming Kwok，Xu Yongzhi Xu

来源：

Accepted to 2019 AAAI Conference on Artificial Intelligence (AAAI)

Computer Vision and Pattern Recognition (cs.CV)

(Submitted on 24 Jan 2019)

链接：

https://arxiv.org/abs/1901.08373

摘要

在点云中检测3D对象的任务在许多实际应用中具有关键作用。然而，由于缺乏强大的3D特征提取方法，3D对象检测性能落后于2D对象检测。为了解决这个问题，我们建议建立一个3D骨干网络，通过使用稀疏3D CNN操作在点云中进行三维物体检测来学习丰富的三维特征图。3D骨干网络可以从几乎原始数据中固有地学习3D特征，而无需将点云压缩为多个2D图像并生成用于对象检测的丰富特征图。稀疏的3D CNN充分利用了3D点云的稀疏性，加速了计算，节省了内存，使得3D骨干网络成为可能。

要点

图:三维骨干网:SSCNN为子流形稀疏3D CNN, SCNN为稀疏3D CNN, DCNN为arse 3D反卷积神经网络，K和S分别为卷积核和stride。

英文原文

The task of detecting 3D objects in point cloud has a pivotal role in many real-world applications. However, 3D object detection performance is behind that of 2D object detection due to the lack of powerful 3D feature extraction methods. In order to address this issue, we propose to build a 3D backbone network to learn rich 3D feature maps by using sparse 3D CNN operations for 3D object detection in point cloud. The 3D backbone network can inherently learn 3D features from almost raw data without compressing point cloud into multiple 2D images and generate rich feature maps for object detection. The sparse 3D CNN takes full advantages of the sparsity in the 3D point cloud to accelerate computation and save memory, which makes the 3D backbone network achievable. Empirical experiments are conducted on the KITTI benchmark and results show that the proposed method can achieve state-of-the-art performance for 3D object detection.