Sim2Real 3D Object Classification using Spherical Kernel Point Convolution and a Deep Center Voting Scheme

TL;DR

This paper introduces a novel spherical kernel point convolution method combined with a deep voting scheme to improve 3D object classification transfer from artificial to real data, addressing shape representation challenges.

Contribution

It proposes spherical kernel point convolutions on surface graphs and a voting scheme to enhance sim2real transfer in 3D classification tasks.

Findings

Achieves up to 36% improvement in sim2real transfer accuracy.

Outperforms state-of-the-art methods on real-world datasets.

Addresses shape representation issues in 3D object classification.

Abstract

While object semantic understanding is essential for most service robotic tasks, 3D object classification is still an open problem. Learning from artificial 3D models alleviates the cost of annotation necessary to approach this problem, but most methods still struggle with the differences existing between artificial and real 3D data. We conjecture that the cause of those issue is the fact that many methods learn directly from point coordinates, instead of the shape, as the former is hard to center and to scale under variable occlusions reliably. We introduce spherical kernel point convolutions that directly exploit the object surface, represented as a graph, and a voting scheme to limit the impact of poor segmentation on the classification results. Our proposed approach improves upon state-of-the-art methods by up to 36% when transferring from artificial objects to real objects.