Cross-view Domain Generalization via Geometric Consistency for LiDAR Semantic Segmentation

2026-02-16

AI Summary

This work addresses the challenge of domain generalization in LiDAR semantic segmentation across divergent viewpoints—such as those from vehicle-mounted and drone-based sensors—where structural incompleteness and uneven point density hinder performance. To this end, we present the first systematic study of this cross-view scenario and introduce the Cross-View Geometry Consistency (CVGC) framework. CVGC employs a cross-view geometric augmentation module to simulate diverse observation perspectives and enforces a geometric consistency constraint that aligns semantic and occupancy predictions across multiple views of the same scene. Extensive experiments on six public LiDAR datasets demonstrate that CVGC significantly outperforms state-of-the-art methods when generalizing from a single source domain to multiple heterogeneous target domains, thereby validating the effectiveness and generality of the proposed geometric consistency mechanism.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Multi-instance/Multi-view Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Web applications in cross-disciplinary domains and verticals such as mixed reality, smart cities, and digital health

Abstract

Domain-generalized LiDAR semantic segmentation (LSS) seeks to train models on source-domain point clouds that generalize reliably to multiple unseen target domains, which is essential for real-world LiDAR applications. However, existing approaches assume similar acquisition views (e.g., vehicle-mounted) and struggle in cross-view scenarios, where observations differ substantially due to viewpoint-dependent structural incompleteness and non-uniform point density. Accordingly, we formulate cross-view domain generalization for LiDAR semantic segmentation and propose a novel framework, termed CVGC (Cross-View Geometric Consistency). Specifically, we introduce a cross-view geometric augmentation module that models viewpoint-induced variations in visibility and sampling density, generating multiple cross-view observations of the same scene. Subsequently, a geometric consistency module enforces consistent semantic and occupancy predictions across geometrically augmented point clouds of the same scene. Extensive experiments on six public LiDAR datasets establish the first systematic evaluation of cross-view domain generalization for LiDAR semantic segmentation, demonstrating that CVGC consistently outperforms state-of-the-art methods when generalizing from a single source domain to multiple target domains with heterogeneous acquisition viewpoints. The source code will be publicly available at https://github.com/KintomZi/CVGC-DG

Problem

• LiDAR semantic segmentation
• domain generalization
• cross-view
• geometric consistency
• point cloud

Innovation

• Cross-view Domain Generalization
• Geometric Consistency
• LiDAR Semantic Segmentation
• Viewpoint Augmentation
• Point Cloud Generalization