Multi-level 3D CNN for Learning Multi-scale Spatial Features

TL;DR

This paper introduces a multi-level 3D CNN that learns multi-scale spatial features from voxel grids, improving 3D object recognition efficiency by reducing memory use while maintaining accuracy.

Contribution

The paper proposes an end-to-end multi-level voxel grid approach for 3D object recognition, addressing resolution and data uniformity challenges in existing methods.

Findings

Achieves comparable accuracy to dense voxel methods.

Uses significantly less memory than traditional dense voxel representations.

Demonstrates effective multi-scale feature learning for 3D object recognition.

Abstract

3D object recognition accuracy can be improved by learning the multi-scale spatial features from 3D spatial geometric representations of objects such as point clouds, 3D models, surfaces, and RGB-D data. Current deep learning approaches learn such features either using structured data representations (voxel grids and octrees) or from unstructured representations (graphs and point clouds). Learning features from such structured representations is limited by the restriction on resolution and tree depth while unstructured representations creates a challenge due to non-uniformity among data samples. In this paper, we propose an end-to-end multi-level learning approach on a multi-level voxel grid to overcome these drawbacks. To demonstrate the utility of the proposed multi-level learning, we use a multi-level voxel representation of 3D objects to perform object recognition. The multi-level voxel representation consists of a coarse voxel grid that contains volumetric information of the 3D object. In addition, each voxel in the coarse grid that contains a portion of the object boundary is subdivided into multiple fine-level voxel grids. The performance of our multi-level learning algorithm for object recognition is comparable to dense voxel representations while using significantly lower memory.