# BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation

arXiv: https://arxiv.org/abs/2308.06530 · HTML: https://mlsanity.com/paper/2308.06530/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 44 references that are in the map.
- First posted on arXiv 12 Aug 2023.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Domain Generalization by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1903.06864/) (2019)
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://mlsanity.com/paper/1711.09869/) (2017)
- [Unified Deep Supervised Domain Adaptation and Generalization](https://mlsanity.com/paper/1709.10190/) (2017)
- [Learning to Learn Single Domain Generalization](https://mlsanity.com/paper/2003.13216/) (2020)
- [Learning to Generate Novel Domains for Domain Generalization](https://mlsanity.com/paper/2007.03304/) (2020)
- [PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation](https://mlsanity.com/paper/2003.14032/) (2020)
- [Generalizing Across Domains via Cross-Gradient Training](https://mlsanity.com/paper/1804.10745/) (2018)
- [Episodic Training for Domain Generalization](https://mlsanity.com/paper/1902.00113/) (2019)
- [Deep Domain-Adversarial Image Generation for Domain Generalisation](https://mlsanity.com/paper/2003.06054/) (2020)
- [A2D2: Audi Autonomous Driving Dataset](https://mlsanity.com/paper/2004.06320/) (2020)
- [Efficient Domain Generalization via Common-Specific Low-Rank Decomposition](https://mlsanity.com/paper/2003.12815/) (2020)
- [xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/1911.12676/) (2019)
- [Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds](https://mlsanity.com/paper/2007.08488/) (2020)
- [ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics](https://mlsanity.com/paper/1908.06295/) (2019)
- [Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds](https://mlsanity.com/paper/2003.13035/) (2020)
- [Domain Generalization via Multidomain Discriminant Analysis](https://mlsanity.com/paper/1907.11216/) (2019)
- [Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2107.14724/) (2021)
- [Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labels](https://mlsanity.com/paper/2004.04091/) (2020)

## Built on by (most cited first, 14 of 14)

- [Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models](https://mlsanity.com/paper/2501.18592/) (2025)
- [Learning to Adapt SAM for Segmenting Cross-domain Point Clouds](https://mlsanity.com/paper/2310.08820/) (2023)
- [DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding](https://mlsanity.com/paper/2407.08801/) (2024)
- [V2X-DGW: Domain Generalization for Multi-agent Perception under Adverse Weather Conditions](https://mlsanity.com/paper/2403.11371/) (2024)
- [OccRWKV: Rethinking Efficient 3D Semantic Occupancy Prediction with Linear Complexity](https://mlsanity.com/paper/2409.19987/) (2024)
- [Hierarchical Context Alignment with Disentangled Geometric and Temporal Modeling for Semantic Occupancy Prediction](https://mlsanity.com/paper/2412.08243/) (2024)
- [Rethinking LiDAR Domain Generalization: Single Source as Multiple Density Domains](https://mlsanity.com/paper/2312.12098/) (2023)
- [Scaling Multi-Camera 3D Object Detection through Weak-to-Strong Eliciting](https://mlsanity.com/paper/2404.06700/) (2024)
- [DaF-BEVSeg: Distortion-aware Fisheye Camera based Bird's Eye View Segmentation with Occlusion Reasoning](https://mlsanity.com/paper/2404.06352/) (2024)
- [Semi-Supervised Semantic Segmentation via Derivative Label Propagation](https://mlsanity.com/paper/2508.02254/) (2025)
- [Cross-view Domain Generalization via Geometric Consistency for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2602.14525/) (2026)
- [Adaptive Augmentation-Aware Latent Learning for Robust LiDAR Semantic Segmentation](https://mlsanity.com/paper/2603.01074/) (2026)
- [ProOOD: Prototype-Guided Out-of-Distribution 3D Occupancy Prediction](https://mlsanity.com/paper/2604.01081/) (2026)
- [EagleVision: A Multi-Task Benchmark for Cross-Domain Perception in High-Speed Autonomous Racing](https://mlsanity.com/paper/2604.11400/) (2026)

## Abstract (arXiv)

Cross-modal Unsupervised Domain Adaptation (UDA) aims to exploit the complementarity of 2D-3D data to overcome the lack of annotation in a new domain. However, UDA methods rely on access to the target domain during training, meaning the trained model only works in a specific target domain. In light of this, we propose cross-modal learning under bird's-eye view for Domain Generalization (DG) of 3D semantic segmentation, called BEV-DG. DG is more challenging because the model cannot access the target domain during training, meaning it needs to rely on cross-modal learning to alleviate the domain gap. Since 3D semantic segmentation requires the classification of each point, existing cross-modal learning is directly conducted point-to-point, which is sensitive to the misalignment in projections between pixels and points. To this end, our approach aims to optimize domain-irrelevant representation modeling with the aid of cross-modal learning under bird's-eye view. We propose BEV-based Area-to-area Fusion (BAF) to conduct cross-modal learning under bird's-eye view, which has a higher fault tolerance for point-level misalignment. Furthermore, to model domain-irrelevant representations, we propose BEV-driven Domain Contrastive Learning (BDCL) with the help of cross-modal learning under bird's-eye view. We design three domain generalization settings based on three 3D datasets, and BEV-DG significantly outperforms state-of-the-art competitors with tremendous margins in all settings.