swMATH ID: 36665
Software Authors: Gernot Riegler, Ali Osman Ulusoy, Andreas Geiger
Description: OctNet: Learning Deep 3D Representations at High Resolutions. 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.
Homepage: https://arxiv.org/abs/1611.05009
Source Code: https://github.com/griegler/octnet
Dependencies: Python
Related Software: PointNet; VoxNet; ImageNet; VoxelNet; PointCNN; SPLATNet; PointSIFT; KITTI; DeepLab; ShapeNet; AlexNet; SqueezeSegV2; SnapNet; Faster R-CNN; YOLO; SYNTHIA Dataset; ScanNet; Mapillary Vistas; Grad-CAM; MinkowskiEngine
Cited in: 11 Publications

Citations by Year