mlsanityData to 14 Oct 2026

DualCross: Cross-Modality Cross-Domain Adaptation for Monocular BEV Perception

arXiv 2305.03724 ↗First posted 5 May 2023cs.CV cs.AI cs.ROcited by 8

Not on the map. Why?

Abstract (arXiv)

Closing the domain gap between training and deployment and incorporating multiple sensor modalities are two challenging yet critical topics for self-driving. Existing work only focuses on single one of the above topics, overlooking the simultaneous domain and modality shift which pervasively exists in real-world scenarios. A model trained with multi-sensor data collected in Europe may need to run in Asia with a subset of input sensors available. In this work, we propose DualCross, a cross-modality cross-domain adaptation framework to facilitate the learning of a more robust monocular bird's-eye-view (BEV) perception model, which transfers the point cloud knowledge from a LiDAR sensor in one domain during the training phase to the camera-only testing scenario in a different domain. This work results in the first open analysis of cross-domain cross-sensor perception and adaptation for monocular 3D tasks in the wild. We benchmark our approach on large-scale datasets under a wide range of domain shifts and show state-of-the-art results against various baselines.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 47 of its 55 references that are in the map. First posted on arXiv 5 May 2023.

Builds on

47 of 55 references.

References · 47

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  5. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  6. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  7. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,044
  8. 2019Improved Knowledge Distillation via Teacher Assistantcited by 573
  9. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 572
  10. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 457
  11. 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
  12. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 447
35 more
  1. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 443
  2. 2019On the Efficacy of Knowledge Distillationcited by 381
  3. 2019M3D-RPN: Monocular 3D Region Proposal Network for Object Detectioncited by 252
  4. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  5. 2020Multi-Task Multi-Sensor Fusion for 3D Object Detectioncited by 203
  6. 2018Orthographic Feature Transform for Monocular 3D Object Detectioncited by 202
  7. 2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
  8. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 191
  9. 20203D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detectioncited by 176
  10. 2019Cross-view Semantic Segmentation for Sensing Surroundingscited by 174
  11. 2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 159
  12. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 158
  13. 2019xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentationcited by 129
  14. 2021Cross-Domain Adaptive Teacher for Object Detectioncited by 126
  15. 2020ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votescited by 119
  16. 2019PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representationcited by 114
  17. 2019Monocular 3D Object Detection with Pseudo-LiDAR Point Cloudcited by 113
  18. 2020GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learningcited by 113
  19. 2021Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Imagescited by 98
  20. 2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 94
  21. 2021LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detectorcited by 70
  22. 2022MonoDistill: Learning Spatial Features for Monocular 3D Object Detectioncited by 68
  23. 2022BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detectioncited by 66
  24. 2021Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistencycited by 63
  25. 2019Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimationcited by 61
  26. 2021Object DGCNN: 3D Object Detection using Dynamic Graphscited by 58
  27. 2020FISHING Net: Future Inference of Semantic Heatmaps In Gridscited by 55
  28. 2018AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimationcited by 54
  29. 2020MonoLayout: Amodal scene layout from a single imagecited by 49
  30. 2022Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detectioncited by 48
  31. 2021Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentationcited by 46
  32. 2020mDALU: Multi-Source Domain Adaptation and Label Unification with Partial Datasetscited by 19
  33. 2020Cross-Modality 3D Object Detectioncited by 12
  34. 2021Multi-Modality Task Cascade for 3D Object Detectioncited by 7
  35. 2021Multi-Echo LiDAR for 3D Object Detectioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 3; 2026: 2.

8 papers.

  1. 2024Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Drivingcited by 41
  2. 2025Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Modelscited by 23
  3. 2024Exploring Semi-Supervised Learning for Online Mappingcited by 6
  4. 2024PCT: Perspective Cue Training Framework for Multi-Camera BEV Segmentationcited by 5
  5. 2025HierDAMap: Towards Universal Domain Adaptive BEV Mapping via Hierarchical Perspective Priorscited by 2
  6. 2025NRSeg: Noise-Resilient Learning for BEV Semantic Segmentation via Driving World Modelscited by 2
  7. 2026XD-MAP: Cross-Modal Domain Adaptation via Semantic Parametric Maps for Scalable Training Data Generationcited by 0
  8. 2026PanDA: Unsupervised Domain Adaptation for Multimodal 3D Panoptic Segmentation in Autonomous Drivingcited by 0