Contextual Range-View Projection for 3D LiDAR Point Clouds

TL;DR

This paper introduces contextual range-view projection methods, CAP and CWAP, that improve 3D LiDAR point cloud processing by preserving more relevant points and enhancing class-specific accuracy in range images.

Contribution

It extends traditional depth-based projection by incorporating contextual information, leading to better point retention and class-aware projection strategies.

Findings

CAP improves instance point preservation by up to 3.1% mIoU.

CWAP enhances class-specific segmentation performance.

Proposed methods outperform baseline in SemanticKITTI evaluations.

Abstract

Range-view projection provides an efficient method for transforming 3D LiDAR point clouds into 2D range image representations, enabling effective processing with 2D deep learning models. However, a major challenge in this projection is the many-to-one conflict, where multiple 3D points are mapped onto the same pixel in the range image, requiring a selection strategy. Existing approaches typically retain the point with the smallest depth (closest to the LiDAR), disregarding semantic relevance and object structure, which leads to the loss of important contextual information. In this paper, we extend the depth-based selection rule by incorporating contextual information from both instance centers and class labels, introducing two mechanisms: \textit{Centerness-Aware Projection (CAP)} and \textit{Class-Weighted-Aware Projection (CWAP)}. In CAP, point depths are adjusted according to their distance from the instance center, thereby prioritizing central instance points over noisy boundary and background points. In CWAP, object classes are prioritized through user-defined weights, offering flexibility in the projection strategy. Our evaluations on the SemanticKITTI dataset show that CAP preserves more instance points during projection, achieving up to a 3.1\% mIoU improvement compared to the baseline. Furthermore, CWAP enhances the performance of targeted classes while having a negligible impact on the performance of other classes