LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment

TL;DR

This paper introduces LCPS, a novel LiDAR-Camera panoptic segmentation network that effectively fuses sensor data through three modules, significantly improving segmentation performance on the NuScenes dataset.

Contribution

The paper presents the first LiDAR-Camera panoptic segmentation network with a three-stage fusion strategy, including calibration, semantic-aware alignment, and feature propagation.

Findings

Achieves 6.9% higher PQ than LiDAR-only baseline on NuScenes

Demonstrates the effectiveness of multi-stage fusion modules

Provides extensive experiments validating the approach

Abstract

3D panoptic segmentation is a challenging perception task that requires both semantic segmentation and instance segmentation. In this task, we notice that images could provide rich texture, color, and discriminative information, which can complement LiDAR data for evident performance improvement, but their fusion remains a challenging problem. To this end, we propose LCPS, the first LiDAR-Camera Panoptic Segmentation network. In our approach, we conduct LiDAR-Camera fusion in three stages: 1) an Asynchronous Compensation Pixel Alignment (ACPA) module that calibrates the coordinate misalignment caused by asynchronous problems between sensors; 2) a Semantic-Aware Region Alignment (SARA) module that extends the one-to-one point-pixel mapping to one-to-many semantic relations; 3) a Point-to-Voxel feature Propagation (PVP) module that integrates both geometric and semantic fusion information for the entire point cloud. Our fusion strategy improves about 6.9% PQ performance over the LiDAR-only baseline on NuScenes dataset. Extensive quantitative and qualitative experiments further demonstrate the effectiveness of our novel framework. The code will be released at https://github.com/zhangzw12319/lcps.git.