# Towards Domain Generalization for Multi-view 3D Object Detection in Bird-Eye-View

arXiv: https://arxiv.org/abs/2303.01686 · HTML: https://mlsanity.com/paper/2303.01686/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 44 references that are in the map.
- First posted on arXiv 3 Mar 2023.

## Builds on (most cited first, 30 of 36)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/1808.00897/) (2018)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection](https://mlsanity.com/paper/2206.10092/) (2022)
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022)
- [FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection](https://mlsanity.com/paper/2104.10956/) (2021)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [Learning Deconvolution Network for Semantic Segmentation](https://mlsanity.com/paper/1505.04366/) (2015)
- [Is Pseudo-Lidar needed for Monocular 3D Object detection?](https://mlsanity.com/paper/2108.06417/) (2021)
- [Exploring Categorical Regularization for Domain Adaptive Object Detection](https://mlsanity.com/paper/2003.09152/) (2020)
- [Vision-Centric BEV Perception: A Survey](https://mlsanity.com/paper/2208.02797/) (2022)
- [CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth](https://mlsanity.com/paper/1904.02028/) (2019)
- [AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2201.06493/) (2022)
- [Multi-Modal 3D Object Detection in Autonomous Driving: a Survey](https://mlsanity.com/paper/2106.12735/) (2021)

## Built on by (most cited first, 27 of 27)

- [Stream Query Denoising for Vectorized HD Map Construction](https://mlsanity.com/paper/2401.09112/) (2024)
- [DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving](https://mlsanity.com/paper/2412.09043/) (2024)
- [TIMotion: Temporal and Interactive Framework for Efficient Human-Human Motion Generation](https://mlsanity.com/paper/2408.17135/) (2024)
- [DVGT: Driving Visual Geometry Transformer](https://mlsanity.com/paper/2512.16919/) (2025)
- [A Survey of Label-Efficient Deep Learning for 3D Point Clouds](https://mlsanity.com/paper/2305.19812/) (2023)
- [DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding](https://mlsanity.com/paper/2407.08801/) (2024)
- [Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2410.22461/) (2024)
- [PhysMLE: Generalizable and Priors-Inclusive Multi-task Remote Physiological Measurement](https://mlsanity.com/paper/2405.06201/) (2024)
- [Towards Generalizable Multi-Camera 3D Object Detection via Perspective Debiasing](https://mlsanity.com/paper/2310.11346/) (2023)
- [4D Driving Scene Generation With Stereo Forcing](https://mlsanity.com/paper/2509.20251/) (2025)
- [Scaling Multi-Camera 3D Object Detection through Weak-to-Strong Eliciting](https://mlsanity.com/paper/2404.06700/) (2024)
- [Benchmarking Cross-Domain Audio-Visual Deception Detection](https://mlsanity.com/paper/2405.06995/) (2024)
- [DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perception](https://mlsanity.com/paper/2401.08687/) (2024)
- [MapGS: Generalizable Pretraining and Data Augmentation for Online Mapping via Novel View Synthesis](https://mlsanity.com/paper/2501.06660/) (2025)
- [RendBEV: Semantic Novel View Synthesis for Self-Supervised Bird's Eye View Segmentation](https://mlsanity.com/paper/2502.14792/) (2025)
- [123D: Unifying Multi-Modal Autonomous Driving Data at Scale](https://mlsanity.com/paper/2605.08084/) (2026)
- [Fully Test-Time Adaptation for Monocular 3D Object Detection](https://mlsanity.com/paper/2405.19682/) (2024)
- [MARRS: Masked Autoregressive Unit-based Reaction Synthesis](https://mlsanity.com/paper/2505.11334/) (2025)
- [Stereo-based 3D Anomaly Object Detection for Autonomous Driving: A New Dataset and Baseline](https://mlsanity.com/paper/2507.09214/) (2025)
- [LiteFusion: Taming 3D Object Detectors from Vision-Based to Multi-Modal with Minimal Adaptation](https://mlsanity.com/paper/2512.20217/) (2025)
- [GOOD: Towards Domain Generalized Orientated Object Detection](https://mlsanity.com/paper/2402.12765/) (2024)
- [UniDrive: Towards Universal Driving Perception Across Camera Configurations](https://mlsanity.com/paper/2410.13864/) (2024)
- [NexusFlow: Unifying Disparate Tasks under Partial Supervision via Invertible Flow Networks](https://mlsanity.com/paper/2512.06251/) (2025)
- [LCF3D: A Robust and Real-Time Late-Cascade Fusion Framework for 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/2601.09812/) (2026)
- [PhysiGen: Integrating Collision-Aware Physical Constraints for High-Fidelity Human-Human Interaction Generation](https://mlsanity.com/paper/2605.00517/) (2026)
- [MAGneT-3D: Monocular and Domain-Generalizable Temporal 3D Detection](https://mlsanity.com/paper/2608.14282/) (2026)
- [Syn2RealTrack: Bridging the Gap Between Synthetic and Real-World Datasets for Online Multi-View Multi-Target Tracking](https://mlsanity.com/paper/2608.24130/) (2026)

## Abstract (arXiv)

Multi-view 3D object detection (MV3D-Det) in Bird-Eye-View (BEV) has drawn extensive attention due to its low cost and high efficiency. Although new algorithms for camera-only 3D object detection have been continuously proposed, most of them may risk drastic performance degradation when the domain of input images differs from that of training. In this paper, we first analyze the causes of the domain gap for the MV3D-Det task. Based on the covariate shift assumption, we find that the gap mainly attributes to the feature distribution of BEV, which is determined by the quality of both depth estimation and 2D image's feature representation. To acquire a robust depth prediction, we propose to decouple the depth estimation from the intrinsic parameters of the camera (i.e. the focal length) through converting the prediction of metric depth to that of scale-invariant depth and perform dynamic perspective augmentation to increase the diversity of the extrinsic parameters (i.e. the camera poses) by utilizing homography. Moreover, we modify the focal length values to create multiple pseudo-domains and construct an adversarial training loss to encourage the feature representation to be more domain-agnostic. Without bells and whistles, our approach, namely DG-BEV, successfully alleviates the performance drop on the unseen target domain without impairing the accuracy of the source domain. Extensive experiments on various public datasets, including Waymo, nuScenes, and Lyft, demonstrate the generalization and effectiveness of our approach. To the best of our knowledge, this is the first systematic study to explore a domain generalization method for MV3D-Det.