TransUPR: A Transformer-based Uncertain Point Refiner for LiDAR Point Cloud Semantic Segmentation

TL;DR

TransUPR introduces a transformer-based uncertain point refiner that enhances LiDAR point cloud segmentation by focusing on boundary regions, achieving state-of-the-art results with minimal additional computation.

Contribution

A novel transformer-based refiner for uncertain points that can be integrated into existing LiDAR segmentation methods, improving boundary accuracy and overall performance.

Findings

Achieved 68.2% mIoU on Semantic KITTI benchmark.

Improved segmentation performance by 0.6% mIoU over CENet.

Refiner is independent of 2D CNNs, enabling easy integration.

Abstract

Common image-based LiDAR point cloud semantic segmentation (LiDAR PCSS) approaches have bottlenecks resulting from the boundary-blurring problem of convolution neural networks (CNNs) and quantitation loss of spherical projection. In this work, we propose a transformer-based plug-and-play uncertain point refiner, i.e., TransUPR, to refine selected uncertain points in a learnable manner, which leads to an improved segmentation performance. Uncertain points are sampled from coarse semantic segmentation results of 2D image segmentation where uncertain points are located close to the object boundaries in the 2D range image representation and 3D spherical projection background points. Following that, the geometry and coarse semantic features of uncertain points are aggregated by neighbor points in 3D space without adding expensive computation and memory footprint. Finally, the transformer-based refiner, which contains four stacked self-attention layers, along with an MLP module, is utilized for uncertain point classification on the concatenated features of self-attention layers. As the proposed refiner is independent of 2D CNNs, our TransUPR can be easily integrated into any existing image-based LiDAR PCSS approaches, e.g., CENet. Our TransUPR with the CENet achieves state-of-the-art performance, i.e., 68.2% mean Intersection over Union (mIoU) on the Semantic KITTI benchmark, which provides a performance improvement of 0.6% on the mIoU compared to the original CENet.