mlsanityData to 7 Oct 2026

SupFusion: Supervised LiDAR-Camera Fusion for 3D Object Detection

arXiv 2309.07084 ↗First posted 13 Sep 2023cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a novel training strategy called SupFusion, which provides an auxiliary feature level supervision for effective LiDAR-Camera fusion and significantly boosts detection performance. Our strategy involves a data enhancement method named Polar Sampling, which densifies sparse objects and trains an assistant model to generate high-quality features as the supervision. These features are then used to train the LiDAR-Camera fusion model, where the fusion feature is optimized to simulate the generated high-quality features. Furthermore, we propose a simple yet effective deep fusion module, which contiguously gains superior performance compared with previous fusion methods with SupFusion strategy. In such a manner, our proposal shares the following advantages. Firstly, SupFusion introduces auxiliary feature-level supervision which could boost LiDAR-Camera detection performance without introducing extra inference costs. Secondly, the proposed deep fusion could continuously improve the detector's abilities. Our proposed SupFusion and deep fusion module is plug-and-play, we make extensive experiments to demonstrate its effectiveness. Specifically, we gain around 2% 3D mAP improvements on KITTI benchmark based on multiple LiDAR-Camera 3D detectors.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 50 of its 58 references that are in the map. First posted on arXiv 13 Sep 2023.

Builds on

50 of 58 references.

References · 50

  1. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  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. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  6. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,147
  9. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  10. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  11. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  12. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
38 more
  1. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  2. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  3. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  4. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  5. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  6. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 334
  7. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 326
  8. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
  9. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  10. 2022DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detectioncited by 224
  11. 2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
  12. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 190
  13. 2019Distilling Object Detectors with Fine-grained Feature Imitationcited by 188
  14. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 184
  15. 20203D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detectioncited by 176
  16. 2021Multimodal Virtual Point 3D Detectioncited by 166
  17. 2020EPNet: Enhancing Point Features with Image Semantics for 3D Object Detectioncited by 164
  18. 2019MVX-Net: Multimodal VoxelNet for 3D Object Detectioncited by 162
  19. 2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 155
  20. 2020Pillar-based Object Detection for Autonomous Drivingcited by 137
  21. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  22. 2022Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Datacited by 126
  23. 2019Fast Point R-CNNcited by 119
  24. 2021General Instance Distillation for Object Detectioncited by 113
  25. 2021Distilling Object Detectors via Decoupled Featurescited by 105
  26. 2022PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detectioncited by 99
  27. 2021AutoShape: Real-Time Shape-Aware Monocular 3D Object Detectioncited by 87
  28. 2021Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detectioncited by 84
  29. 2022Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completioncited by 82
  30. 2021Monocular 3D Object Detection: An Extrinsic Parameter Free Approachcited by 69
  31. 2021LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detectorcited by 69
  32. 2022MonoDistill: Learning Spatial Features for Monocular 3D Object Detectioncited by 68
  33. 2021GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detectioncited by 66
  34. 2022BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detectioncited by 66
  35. 2021Progressive Coordinate Transforms for Monocular 3D Object Detectioncited by 52
  36. 2022Voxel Field Fusion for 3D Object Detectioncited by 50
  37. 2022Boosting 3D Object Detection by Simulating Multimodality on Point Cloudscited by 22
  38. 2022Paint and Distill: Boosting 3D Object Detection with Semantic Passing Networkcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 6; 2026: 2.

14 papers.

Sort:

By area:

  1. 2024Co-Occ: Coupling Explicit Feature Fusion with Volume Rendering Regularization for Multi-Modal 3D Semantic Occupancy Predictioncited by 46
  2. 2023MUVO: A Multimodal Generative World Model for Autonomous Driving with Geometric Representationscited by 33
  3. 2024AD-H: Language-guided Autonomous Driving with Hierarchical Agentscited by 15
  4. 2025NavigateDiff: Visual Predictors are Zero-Shot Navigation Assistantscited by 11
  5. 2024Multi-Modal UAV Detection, Classification and Tracking Algorithm -- Technical Report for CVPR 2024 UG2 Challengecited by 9
  6. 2025BevSplat: Resolving Height Ambiguity via Feature-Based Gaussian Primitives for Weakly-Supervised Cross-View Localizationcited by 7
  7. 2024PVP: Polar Representation Boost for 3D Semantic Occupancy Predictioncited by 2
  8. 2025CRAB: Camera-Radar Fusion for Reducing Depth Ambiguity in Backward Projection based View Transformationcited by 2
  9. 2025KD360-VoxelBEV: LiDAR and 360-degree Camera Cross Modality Knowledge Distillation for Bird's-Eye-View Segmentationcited by 2
  10. 2025LiteFusion: Taming 3D Object Detectors from Vision-Based to Multi-Modal with Minimal Adaptationcited by 1
  11. 2025GeoTeacher: Geometry-Guided Semi-Supervised 3D Object Detectioncited by 1
  12. 2026C2E: Boosting Ego-Only 3D Object Detection via Multi-Teacher Contrastive Knowledge Distillationcited by 1
2 more
  1. 2024KAN-RCBEVDepth: A multi-modal fusion algorithm in object detection for autonomous drivingcited by 0
  2. 2026Efficient UAV trajectory prediction: A multi-modal deep diffusion frameworkcited by 0