Trainable Pointwise Decoder Module for Point Cloud Segmentation

TL;DR

This paper introduces a trainable pointwise decoder module and a data augmentation strategy to improve outdoor point cloud segmentation, enabling end-to-end training and better handling of varying point densities.

Contribution

The paper proposes a novel trainable pointwise decoder module (PDM) and a range image-guided data augmentation method (VRCrop) to enhance point cloud segmentation performance.

Findings

PDM improves segmentation accuracy on outdoor datasets.

VRCrop reduces artifacts and balances point cloud density.

Models with PDM and VRCrop outperform existing methods.

Abstract

Point cloud segmentation (PCS) aims to make per-point predictions and enables robots and autonomous driving cars to understand the environment. The range image is a dense representation of a large-scale outdoor point cloud, and segmentation models built upon the image commonly execute efficiently. However, the projection of the point cloud onto the range image inevitably leads to dropping points because, at each image coordinate, only one point is kept despite multiple points being projected onto the same location. More importantly, it is challenging to assign correct predictions to the dropped points that belong to the classes different from the kept point class. Besides, existing post-processing methods, such as K-nearest neighbor (KNN) search and kernel point convolution (KPConv), cannot be trained with the models in an end-to-end manner or cannot process varying-density outdoor point clouds well, thereby enabling the models to achieve sub-optimal performance. To alleviate this problem, we propose a trainable pointwise decoder module (PDM) as the post-processing approach, which gathers weighted features from the neighbors and then makes the final prediction for the query point. In addition, we introduce a virtual range image-guided copy-rotate-paste (VRCrop) strategy in data augmentation. VRCrop constrains the total number of points and eliminates undesirable artifacts in the augmented point cloud. With PDM and VRCrop, existing range image-based segmentation models consistently perform better than their counterparts on the SemanticKITTI, SemanticPOSS, and nuScenes datasets.