OctNet: Learning Deep 3D Representations at High Resolutions

被引：987

作者：

Riegler, Gernot ^{[1
]}

Ulusoy, Ali Osman ^{[2
]}

Geiger, Andreas ^{[2
,3
]}

机构：

[1] Graz Univ Technol, Inst Comp Graph & Vis, Graz, Austria

[2] MPI Intelligent Syst Tubingen, Autonomous Vis Grp, Tubingen, Germany

[3] Swiss Fed Inst Technol, Comp Vis & Geometry Grp, Zurich, Switzerland

来源：

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) | 2017年

关键词：

D O I：

10.1109/CVPR.2017.701

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present OctNet, a representation for deep learning with sparse 3D data. In contrast to existing models, our representation enables 3D convolutional networks which are both deep and high resolution. Towards this goal, we exploit the sparsity in the input data to hierarchically partition the space using a set of unbalanced octrees where each leaf node stores a pooled feature representation. This allows to focus memory allocation and computation to the relevant dense regions and enables deeper networks without compromising resolution. We demonstrate the utility of our OctNet representation by analyzing the impact of resolution on several 3D tasks including 3D object classification, orientation estimation and point cloud labeling.

引用

页码：6620 / 6629

页数：10