mlsanityData to 7 Oct 2026

Eliminating Cross-modal Conflicts in BEV Space for LiDAR-Camera 3D Object Detection

arXiv 2403.07372 ↗First posted 12 Mar 2024cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Recent 3D object detectors typically utilize multi-sensor data and unify multi-modal features in the shared bird's-eye view (BEV) representation space. However, our empirical findings indicate that previous methods have limitations in generating fusion BEV features free from cross-modal conflicts. These conflicts encompass extrinsic conflicts caused by BEV feature construction and inherent conflicts stemming from heterogeneous sensor signals. Therefore, we propose a novel Eliminating Conflicts Fusion (ECFusion) method to explicitly eliminate the extrinsic/inherent conflicts in BEV space and produce improved multi-modal BEV features. Specifically, we devise a Semantic-guided Flow-based Alignment (SFA) module to resolve extrinsic conflicts via unifying spatial distribution in BEV space before fusion. Moreover, we design a Dissolved Query Recovering (DQR) mechanism to remedy inherent conflicts by preserving objectness clues that are lost in the fusion BEV feature. In general, our method maximizes the effective information utilization of each modality and leverages inter-modal complementarity. Our method achieves state-of-the-art performance in the highly competitive nuScenes 3D object detection dataset. The code is released at https://github.com/fjhzhixi/ECFusion.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 51 of its 58 references that are in the map. First posted on arXiv 12 Mar 2024.

Builds on

51 of 58 references.

References · 51

  1. 2020End-to-End Object Detection with Transformerscited by 7,384
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  6. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  7. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  8. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  9. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  10. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  11. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  12. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
38 more
  1. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  2. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  3. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  4. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  5. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  6. 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
  7. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  8. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  9. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 351
  10. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 334
  11. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  12. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  13. 2020Multi-Task Multi-Sensor Fusion for 3D Object Detectioncited by 203
  14. 2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
  15. 2022FUTR3D: A Unified Sensor Fusion Framework for 3D Detectioncited by 194
  16. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 190
  17. 2016Deep Feature Flow for Video Recognitioncited by 186
  18. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  19. 2021Multimodal Virtual Point 3D Detectioncited by 166
  20. 2020EPNet: Enhancing Point Features with Image Semantics for 3D Object Detectioncited by 164
  21. 2022M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representationcited by 155
  22. 2022PolarFormer: Multi-camera 3D Object Detection with Polar Transformercited by 147
  23. 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
  24. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  25. 2020Semantic Flow for Fast and Accurate Scene Parsingcited by 128
  26. 2022DeepInteraction: 3D Object Detection via Modality Interactioncited by 125
  27. 2020ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votescited by 119
  28. 2022Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completioncited by 82
  29. 2022AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detectioncited by 70
  30. 2022Voxel Field Fusion for 3D Object Detectioncited by 50
  31. 2021VPFNet: Improving 3D Object Detection with Virtual Point based LiDAR and Stereo Data Fusioncited by 48
  32. 2022AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detectioncited by 46
  33. 2022Learning Ego 3D Representation as Ray Tracingcited by 43
  34. 2023Object as Query: Lifting any 2D Object Detector to 3D Detectioncited by 38
  35. 2020RangeRCNN: Towards Fast and Accurate 3D Object Detection with Range Image Representationcited by 37
  36. 2023MonoPGC: Monocular 3D Object Detection with Pixel Geometry Contextscited by 21
  37. 2023Sparse Dense Fusion for 3D Object Detectioncited by 9
  38. 2022Cost-Aware Evaluation and Model Scaling for LiDAR-Based 3D Object Detectioncited by 3

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 4; 2026: 4.

10 papers.

  1. 2024MV2DFusion: Leveraging Modality-Specific Object Semantics for Multi-Modal 3D Detectioncited by 23
  2. 2024Global-Local Collaborative Inference with LLM for Lidar-Based Open-Vocabulary Detectioncited by 10
  3. 2026Geometry-Guided 3D Visual Token Pruning for Video-Language Modelscited by 3
  4. 2025A Novel Multi-layer Task-centric and Data Quality Framework for Autonomous Drivingcited by 2
  5. 2025GLRD: Global-Local Collaborative Reason and Debate with PSL for 3D Open-Vocabulary Detectioncited by 1
  6. 2025SparseVoxFormer: Sparse Voxel-based Transformer for Multi-modal 3D Object Detectioncited by 0
  7. 2025Dual-Domain Homogeneous Fusion with Cross-Modal Mamba and Progressive Decoder for 3D Object Detectioncited by 0
  8. 2026Modeling and Measuring Redundancy in Multisource Multimodal Data for Autonomous Drivingcited by 0
  9. 2026Generative Lane Topology Reasoning via Autoregressive Model with Geometry Priorcited by 0
  10. 2026MATS: A novel multi-modality multi-task learning framework for 3D perception in autonomous drivingcited by 0