PC-BEV: An Efficient Polar-Cartesian BEV Fusion Framework for LiDAR Semantic Segmentation

TL;DR

This paper introduces PC-BEV, a fast and efficient LiDAR segmentation framework that fuses Polar and Cartesian views within the BEV space, achieving high accuracy and speed without relying on computationally intensive point-based methods.

Contribution

It proposes a novel BEV-only fusion approach leveraging fixed grid correspondences between Polar and Cartesian schemes, significantly improving speed and dense feature integration.

Findings

170× faster inference than point-based methods

Outperforms previous multiview fusion approaches in accuracy

Demonstrates effective scene understanding with hybrid Transformer-CNN

Abstract

Although multiview fusion has demonstrated potential in LiDAR segmentation, its dependence on computationally intensive point-based interactions, arising from the lack of fixed correspondences between views such as range view and Bird's-Eye View (BEV), hinders its practical deployment. This paper challenges the prevailing notion that multiview fusion is essential for achieving high performance. We demonstrate that significant gains can be realized by directly fusing Polar and Cartesian partitioning strategies within the BEV space. Our proposed BEV-only segmentation model leverages the inherent fixed grid correspondences between these partitioning schemes, enabling a fusion process that is orders of magnitude faster (170$\times$ speedup) than conventional point-based methods. Furthermore, our approach facilitates dense feature fusion, preserving richer contextual information compared to sparse point-based alternatives. To enhance scene understanding while maintaining inference efficiency, we also introduce a hybrid Transformer-CNN architecture. Extensive evaluation on the SemanticKITTI and nuScenes datasets provides compelling evidence that our method outperforms previous multiview fusion approaches in terms of both performance and inference speed, highlighting the potential of BEV-based fusion for LiDAR segmentation. Code is available at \url{https://github.com/skyshoumeng/PC-BEV.}