mlsanityData to 7 Oct 2026

SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection

arXiv 2307.11477 ↗First posted 21 Jul 2023cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

Recently, the pure camera-based Bird's-Eye-View (BEV) perception provides a feasible solution for economical autonomous driving. However, the existing BEV-based multi-view 3D detectors generally transform all image features into BEV features, without considering the problem that the large proportion of background information may submerge the object information. In this paper, we propose Semantic-Aware BEV Pooling (SA-BEVPool), which can filter out background information according to the semantic segmentation of image features and transform image features into semantic-aware BEV features. Accordingly, we propose BEV-Paste, an effective data augmentation strategy that closely matches with semantic-aware BEV feature. In addition, we design a Multi-Scale Cross-Task (MSCT) head, which combines task-specific and cross-task information to predict depth distribution and semantic segmentation more accurately, further improving the quality of semantic-aware BEV feature. Finally, we integrate the above modules into a novel multi-view 3D object detection framework, namely SA-BEV. Experiments on nuScenes show that SA-BEV achieves state-of-the-art performance. Code has been available at https://github.com/mengtan00/SA-BEV.git.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 39 of its 50 references that are in the map. First posted on arXiv 21 Jul 2023.

Builds on

39 of 50 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020End-to-End Object Detection with Transformerscited by 7,384
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  4. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  5. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  6. 2019Objects as Pointscited by 1,172
  7. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  8. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  9. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  10. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  11. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  12. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
27 more
  1. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  2. 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
  3. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  4. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  5. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  6. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 351
  7. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  8. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  9. 2018PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsingcited by 224
  10. 2020Multi-Task Multi-Sensor Fusion for 3D Object Detectioncited by 203
  11. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 190
  12. 2021Multimodal Virtual Point 3D Detectioncited by 166
  13. 2019An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detectioncited by 163
  14. 2020MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learningcited by 157
  15. 2022PolarFormer: Multi-camera 3D Object Detection with Polar Transformercited by 147
  16. 2019Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentationcited by 141
  17. 2021Probabilistic two-stage detectioncited by 130
  18. 2021SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloudcited by 119
  19. 2022BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereocited by 89
  20. 2022BEVPoolv2: A Cutting-edge Implementation of BEVDet Toward Deploymentcited by 79
  21. 2019What You See is What You Get: Exploiting Visibility for 3D Object Detectioncited by 69
  22. 2020PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detectioncited by 35
  23. 2020Part-Aware Data Augmentation for 3D Object Detection in Point Cloudcited by 34
  24. 2022CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detectioncited by 32
  25. 2023OcTr: Octree-based Transformer for 3D Object Detectioncited by 32
  26. 2021A Simple and Efficient Multi-task Network for 3D Object Detection and Road Understandingcited by 17
  27. 2021Exploring 2D Data Augmentation for 3D Monocular Object Detectioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 15; 2025: 10; 2026: 3.

30 papers.

Sort:

By area:

  1. 2024Vision-based 3D occupancy prediction in autonomous driving: a review and outlookcited by 29
  2. 2025CoSDH: Communication-Efficient Collaborative Perception via Supply-Demand Awareness and Intermediate-Late Hybridizationcited by 27
  3. 2023PointBeV: A Sparse Approach to BeV Predictionscited by 23
  4. 2024CRT-Fusion: Camera, Radar, Temporal Fusion Using Motion Information for 3D Object Detectioncited by 18
  5. 2024Deep Height Decoupling for Precise Vision-based 3D Occupancy Predictioncited by 16
  6. 2024AD-H: Language-guided Autonomous Driving with Hierarchical Agentscited by 15
  7. 2024BEVSpread: Spread Voxel Pooling for Bird's-Eye-View Representation in Vision-based Roadside 3D Object Detectioncited by 15
  8. 2026ResWorld: Temporal Residual World Model for End-to-End Autonomous Drivingcited by 14
  9. 2024SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objectscited by 12
  10. 2024DualBEV: Unifying Dual View Transformation with Probabilistic Correspondencescited by 9
  11. 2023Lift-Attend-Splat: Bird's-eye-view camera-lidar fusion using transformerscited by 8
  12. 2024SparseFusion: Efficient Sparse Multi-Modal Fusion Framework for Long-Range 3D Perceptioncited by 8
18 more
  1. 2024STAL3D: Unsupervised Domain Adaptation for 3D Object Detection via Collaborating Self-Training and Adversarial Learningcited by 6
  2. 2024FSD-BEV: Foreground Self-Distillation for Multi-view 3D Object Detectioncited by 6
  3. 2024LightOcc: Lightweight Spatial Embedding for Efficient Vision-based 3D Occupancy Predictioncited by 6
  4. 2025AugMapNet: Improving Spatial Latent Structure via BEV Grid Augmentation for Enhanced Vectorized Online HD Map Constructioncited by 6
  5. 2025Disentangling Instance and Scene Contexts for 3D Semantic Scene Completioncited by 6
  6. 2024Learning High-resolution Vector Representation from Multi-Camera Images for 3D Object Detectioncited by 4
  7. 2024PolarBEVDet: Exploring Polar Representation for Multi-View 3D Object Detection in Bird's-Eye-Viewcited by 3
  8. 2025HeightFormer: Learning Height Prediction in Voxel Features for Roadside Vision Centric 3D Object Detection via Transformercited by 3
  9. 2025BEVCon: Advancing Bird's Eye View Perception with Contrastive Learningcited by 3
  10. 2024DaF-BEVSeg: Distortion-aware Fisheye Camera based Bird's Eye View Segmentation with Occlusion Reasoningcited by 2
  11. 2024LSSInst: Improving Geometric Modeling in LSS-Based BEV Perception with Instance Representationcited by 2
  12. 2025OcRFDet: Object-Centric Radiance Fields for Multi-View 3D Object Detection in Autonomous Drivingcited by 1
  13. 2025DA-Occ: Direction-Aware 2D Convolution for Efficient and Geometry-Preserving 3D Occupancy Prediction in Autonomous Drivingcited by 1
  14. 2025Dual-Domain Homogeneous Fusion with Cross-Modal Mamba and Progressive Decoder for 3D Object Detectioncited by 0
  15. 2025OnlineBEV: Recurrent Temporal Fusion in Bird's Eye View Representations for Multi-Camera 3D Perceptioncited by 0
  16. 2025MAESTRO: Task-Relevant Optimization via Adaptive Feature Enhancement and Suppression for Multi-task 3D Perceptioncited by 0
  17. 2026CycleBEV: Regularizing View Transformation Networks via View Cycle Consistency for Bird's-Eye-View Semantic Segmentationcited by 0
  18. 2026Towards Real-Time and Adaptable LiDAR Scene Completioncited by 0