UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase

TL;DR

UniSeg is a multi-modal LiDAR segmentation network that fuses RGB images with point cloud views for improved semantic and panoptic segmentation, achieving top results on major benchmarks.

Contribution

The paper introduces UniSeg, a novel unified network that effectively combines multi-view point cloud data with RGB images and proposes the OpenPCSeg codebase for outdoor LiDAR segmentation.

Findings

Achieves top performance on SemanticKITTI, nuScenes, and Waymo datasets.

Ranks 1st in nuScenes LiDAR semantic segmentation challenge.

Provides a comprehensive, reproducible open-source codebase for outdoor LiDAR segmentation.

Abstract

Point-, voxel-, and range-views are three representative forms of point clouds. All of them have accurate 3D measurements but lack color and texture information. RGB images are a natural complement to these point cloud views and fully utilizing the comprehensive information of them benefits more robust perceptions. In this paper, we present a unified multi-modal LiDAR segmentation network, termed UniSeg, which leverages the information of RGB images and three views of the point cloud, and accomplishes semantic segmentation and panoptic segmentation simultaneously. Specifically, we first design the Learnable cross-Modal Association (LMA) module to automatically fuse voxel-view and range-view features with image features, which fully utilize the rich semantic information of images and are robust to calibration errors. Then, the enhanced voxel-view and range-view features are transformed to the point space,where three views of point cloud features are further fused adaptively by the Learnable cross-View Association module (LVA). Notably, UniSeg achieves promising results in three public benchmarks, i.e., SemanticKITTI, nuScenes, and Waymo Open Dataset (WOD); it ranks 1st on two challenges of two benchmarks, including the LiDAR semantic segmentation challenge of nuScenes and panoptic segmentation challenges of SemanticKITTI. Besides, we construct the OpenPCSeg codebase, which is the largest and most comprehensive outdoor LiDAR segmentation codebase. It contains most of the popular outdoor LiDAR segmentation algorithms and provides reproducible implementations. The OpenPCSeg codebase will be made publicly available at https://github.com/PJLab-ADG/PCSeg.