OctNet: Learning Deep 3D Representations at High Resolutions

TL;DR

OctNet introduces a hierarchical octree-based representation that enables deep, high-resolution 3D convolutional networks by efficiently exploiting data sparsity, improving performance on various 3D tasks.

Contribution

The paper presents a novel octree-based deep learning framework for high-resolution 3D data that surpasses previous models in efficiency and depth capabilities.

Findings

Improved 3D object classification accuracy

Enhanced orientation estimation performance

Effective point cloud labeling at high resolutions

Abstract

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.