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

TL;DR

Cross-view differences in LiDAR acquisition create severe domain gaps for semantic segmentation. The authors introduce CVGC, combining Cross-view Geometric Augmentation (CGA) and Geometric Consistency Regularization (GCR) to enforce viewpoint-invariant semantics and occupancy across multiple cross-view variants generated from a single source. They validate on six public LiDAR datasets spanning airborne, UAV, and vehicle-mounted platforms, establishing the first cross-view DG benchmark and demonstrating consistent gains over existing methods. The work highlights the importance of modeling viewpoint-dependent density and visibility and provides a practical, sensor-agnostic approach with publicly available code.

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

Figures (9)

• Figure 1: Challenges in cross-view domain generalization. (a) Conventional DG assumes similar sensing viewpoints across domains, whereas (b) Cross-view DG involves drastically different acquisition geometries, leading to severe density and visibility shifts. We address this challenge by generating view-dependent geometric variants and enforcing consistency across them.
• Figure 2: Overview of the CVGC framework. The framework consists of two main modules: (i) Cross-view Geometric Augmentation (CGA), which generates a view-dependent variant $\mathbf{P}^{\alpha}$ from the source point cloud $\mathbf{P}^s$; and (ii) Geometric Consistency Regularization (GCR), which enforces structural and semantic consistency across variants. A shared backbone predicts point-wise semantics for both views, with semantic consistency and voxel occupancy supervision jointly regularizing the learned representations, using only source-domain data.
• Figure 3: Illustration of the CGA. (a) Viewpoint-agnostic density resampling, which adjusts point cloud scene density via tangent plane-based densification and voxel-based sparsification. (b) Viewpoint-dependent visibility simulation, which constructs occluded scenes based on a spherical projection process.
• Figure 4: Schematic of the occupancy perception head. Point-wise features are aggregated into voxel representations via voxelization and KNN-based interpolation, and processed by sparse convolutional layers to predict voxel occupancy, providing unified geometric supervision across different viewpoints.
• Figure 5: Benchmark for cross-view domain generalization. The six datasets are partitioned into two groups following a one-source, two-target protocol. (a) First-Group Datasets: H3D (UAV) $\rightarrow$ Paris-Lille-3D (MLS) and ISPRS Vaihingen (ALS). (b) Second-Group Experiments: STPLS3D (synthetic UAV) $\rightarrow$ Toronto-3D (MLS) and DALES (ALS).