Towards Explicit Geometry-Reflectance Collaboration for Generalized LiDAR Segmentation in Adverse Weather

TL;DR

This paper introduces a Geometry-Reflectance Collaboration framework for LiDAR segmentation that improves robustness in adverse weather by explicitly separating and collaborating geometric and reflectance features.

Contribution

The paper proposes a novel dual-branch architecture with multi-level feature collaboration to enhance LiDAR segmentation under adverse weather without complex data augmentation.

Findings

Outperforms previous methods on challenging benchmarks.

Achieves state-of-the-art results in adverse weather conditions.

Effectively suppresses unreliable information from geometric and reflectance features.

Abstract

Existing LiDAR semantic segmentation models often suffer from decreased accuracy when exposed to adverse weather conditions. Recent methods addressing this issue focus on enhancing training data through weather simulation or universal augmentation techniques. However, few works have studied the negative impacts caused by the heterogeneous domain shifts in the geometric structure and reflectance intensity of point clouds. In this paper, we delve into this challenge and address it with a novel Geometry-Reflectance Collaboration (GRC) framework that explicitly separates feature extraction for geometry and reflectance. Specifically, GRC employs a dual-branch architecture designed to independently process geometric and reflectance features initially, thereby capitalizing on their distinct characteristic. Then, GRC adopts a robust multi-level feature collaboration module to suppress redundant and unreliable information from both branches. Consequently, without complex simulation or augmentation, our method effectively extracts intrinsic information about the scene while suppressing interference, thus achieving better robustness and generalization in adverse weather conditions. We demonstrate the effectiveness of GRC through comprehensive experiments on challenging benchmarks, showing that our method outperforms previous approaches and establishes new state-of-the-art results.