ProtoSeg: A Prototype-Based Point Cloud Instance Segmentation Method

TL;DR

ProtoSeg introduces a fast, stable, and accurate neural network for 3D point cloud instance segmentation that avoids clustering and employs prototype learning with a novel multi-scale module.

Contribution

It proposes a prototype-based neural network architecture with a multi-scale dilated point inception module for improved 3D instance segmentation.

Findings

28% faster inference than state-of-the-art

Lowest standard deviation in inference time

Outperforms on S3DIS and PartNet datasets

Abstract

3D instance segmentation is crucial for obtaining an understanding of a point cloud scene. This paper presents a novel neural network architecture for performing instance segmentation on 3D point clouds. We propose to jointly learn coefficients and prototypes in parallel which can be combined to obtain the instance predictions. The coefficients are computed using an overcomplete set of sampled points with a novel multi-scale module, dubbed dilated point inception. As the set of obtained instance mask predictions is overcomplete, we employ a non-maximum suppression algorithm to retrieve the final predictions. This approach allows to omit the time-expensive clustering step and leads to a more stable inference time. The proposed method is not only 28% faster than the state-of-the-art, it also exhibits the lowest standard deviation. Our experiments have shown that the standard deviation of the inference time is only 1.0% of the total time while it ranges between 10.8 and 53.1% for the state-of-the-art methods. Lastly, our method outperforms the state-of-the-art both on S3DIS-blocks (4.9% in mRec on Fold-5) and PartNet (2.0% on average in mAP).