mlsanityData to 7 Oct 2026

LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector

arXiv 2108.08258 ↗First posted 18 Aug 2021cs.CVcited by 69

Not on the map. Why?

Abstract (arXiv)

Stereo-based 3D detection aims at detecting 3D object bounding boxes from stereo images using intermediate depth maps or implicit 3D geometry representations, which provides a low-cost solution for 3D perception. However, its performance is still inferior compared with LiDAR-based detection algorithms. To detect and localize accurate 3D bounding boxes, LiDAR-based models can encode accurate object boundaries and surface normal directions from LiDAR point clouds. However, the detection results of stereo-based detectors are easily affected by the erroneous depth features due to the limitation of stereo matching. To solve the problem, we propose LIGA-Stereo (LiDAR Geometry Aware Stereo Detector) to learn stereo-based 3D detectors under the guidance of high-level geometry-aware representations of LiDAR-based detection models. In addition, we found existing voxel-based stereo detectors failed to learn semantic features effectively from indirect 3D supervisions. We attach an auxiliary 2D detection head to provide direct 2D semantic supervisions. Experiment results show that the above two strategies improved the geometric and semantic representation capabilities. Compared with the state-of-the-art stereo detector, our method has improved the 3D detection performance of cars, pedestrians, cyclists by 10.44%, 5.69%, 5.97% mAP respectively on the official KITTI benchmark. The gap between stereo-based and LiDAR-based 3D detectors is further narrowed.

Key facts. Cited by 69 papers in the map (data through 7 Oct 2026). Builds on 59 of its 71 references that are in the map. First posted on arXiv 18 Aug 2021.

Builds on

59 of 71 references.

References · 59

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  5. 2014FitNets: Hints for Thin Deep Netscited by 1,619
  6. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  9. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  10. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  11. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  12. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
38 more
  1. 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 719
  2. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  3. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  4. 2018Pyramid Stereo Matching Networkcited by 486
  5. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  6. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  7. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  8. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 359
  9. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  10. 2019A Comprehensive Overhaul of Feature Distillationcited by 341
  11. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  12. 2019Structured Knowledge Distillation for Dense Predictioncited by 277
  13. 2018Paraphrasing Complex Network: Network Compression via Factor Transfercited by 255
  14. 2016SoundNet: Learning Sound Representations from Unlabeled Videocited by 244
  15. 2019GA-Net: Guided Aggregation Net for End-to-end Stereo Matchingcited by 242
  16. 2019Group-wise Correlation Stereo Networkcited by 235
  17. 2020AANet: Adaptive Aggregation Network for Efficient Stereo Matchingcited by 202
  18. 2019Distilling Object Detectors with Fine-grained Feature Imitationcited by 188
  19. 2019Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Drivingcited by 188
  20. 2015Cross Modal Distillation for Supervision Transfercited by 173
  21. 2020Hierarchical Neural Architecture Search for Deep Stereo Matchingcited by 166
  22. 2019Stereo R-CNN based 3D Object Detection for Autonomous Drivingcited by 163
  23. 2019IoU Loss for 2D/3D Object Detectioncited by 128
  24. 2019Knowledge Adaptation for Efficient Semantic Segmentationcited by 105
  25. 2020DSGN: Deep Stereo Geometry Network for 3D Object Detectioncited by 100
  26. 2017ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenescited by 95
  27. 2018Hierarchical Discrete Distribution Decomposition for Match Density Estimationcited by 93
  28. 2018SegStereo: Exploiting Semantic Information for Disparity Estimationcited by 88
  29. 2019ASR is all you need: cross-modal distillation for lip readingcited by 85
  30. 2020End-to-End Pseudo-LiDAR for Image-Based 3D Object Detectioncited by 80
  31. 2017Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matchingcited by 63
  32. 2018Online Model Distillation for Efficient Video Inferencecited by 60
  33. 20163D Object Proposals using Stereo Imagery for Accurate Object Class Detectioncited by 58
  34. 2019Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matchingcited by 55
  35. 2020Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimationcited by 43
  36. 2019Triangulation Learning Network: from Monocular to Stereo 3D Object Detectioncited by 40
  37. 2020Wasserstein Distances for Stereo Disparity Estimationcited by 38
  38. 2020Knowledge as Priors: Cross-Modal Knowledge Generalization for Datasets without Superior Knowledgecited by 35

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 23; 2023: 21; 2024: 10; 2025: 10; 2026: 2.

69 papers.

Sort:

By area:

  1. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 334
  2. 2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
  3. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  4. 2022Vision-Centric BEV Perception: A Surveycited by 126
  5. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  6. 2023LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusioncited by 80
  7. 2023Bird's-Eye-View Scene Graph for Vision-Language Navigationcited by 71
  8. 2022MonoDistill: Learning Spatial Features for Monocular 3D Object Detectioncited by 68
  9. 20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66
  10. 2022BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detectioncited by 66
  11. 2022Monocular 3D Object Detection with Depth from Motioncited by 38
  12. 2022PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detectioncited by 33
38 more
  1. 2023MonoNeRD: NeRF-like Representations for Monocular 3D Object Detectioncited by 33
  2. 2022Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Drivingcited by 30
  3. 2022Towards Efficient 3D Object Detection with Knowledge Distillationcited by 29
  4. 2023Fully Sparse Fusion for 3D Object Detectioncited by 29
  5. 2023X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detectioncited by 28
  6. 2022LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detectioncited by 27
  7. 2024RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Featurescited by 27
  8. 2024CRKD: Enhanced Camera-Radar Object Detection with Cross-modality Knowledge Distillationcited by 27
  9. 2022Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detectioncited by 26
  10. 2023MonoPGC: Monocular 3D Object Detection with Pixel Geometry Contextscited by 21
  11. 2023GeoMIM: Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understandingcited by 17
  12. 2022itKD: Interchange Transfer-based Knowledge Distillation for 3D Object Detectioncited by 14
  13. 2023SupFusion: Supervised LiDAR-Camera Fusion for 3D Object Detectioncited by 14
  14. 2021SGM3D: Stereo Guided Monocular 3D Object Detectioncited by 13
  15. 2023Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detectioncited by 13
  16. 2024HVDistill: Transferring Knowledge from Images to Point Clouds via Unsupervised Hybrid-View Distillationcited by 11
  17. 2022DSGN++: Exploiting Visual-Spatial Relation for Stereo-based 3D Detectorscited by 10
  18. 2022ORA3D: Overlap Region Aware Multi-view 3D Object Detectioncited by 8
  19. 2023Geometric-aware Pretraining for Vision-centric 3D Object Detectioncited by 8
  20. 2023DualCross: Cross-Modality Cross-Domain Adaptation for Monocular BEV Perceptioncited by 8
  21. 2023Lift-Attend-Splat: Bird's-eye-view camera-lidar fusion using transformerscited by 8
  22. 2025Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event Camerascited by 8
  23. 2021ESGN: Efficient Stereo Geometry Network for Fast 3D Object Detectioncited by 7
  24. 2022Attention-Based Depth Distillation with 3D-Aware Positional Encoding for Monocular 3D Object Detectioncited by 7
  25. 2023StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-based 3D Object Detectioncited by 7
  26. 20233D Video Object Detection with Learnable Object-Centric Global Optimizationcited by 7
  27. 2023Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceivercited by 7
  28. 2024Improving Distant 3D Object Detection Using 2D Box Supervisioncited by 6
  29. 2024FSD-BEV: Foreground Self-Distillation for Multi-view 3D Object Detectioncited by 6
  30. 2025Is Discretization Fusion All You Need for Collaborative Perception?cited by 6
  31. 2024DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perceptioncited by 5
  32. 2024Cross-View Consistency Regularisation for Knowledge Distillationcited by 5
  33. 2022Stereo Neural Vernier Calipercited by 3
  34. 2022Structured Knowledge Distillation Towards Efficient and Compact Multi-View 3D Detectioncited by 3
  35. 2025Unleashing the Temporal Potential of Stereo Event Cameras for Continuous-Time 3D Object Detectioncited by 3
  36. 2025RCTDistill: Cross-Modal Knowledge Distillation Framework for Radar-Camera 3D Object Detection with Temporal Fusioncited by 3
  37. 2022An Empirical Study of Pseudo-Labeling for Image-based 3D Object Detectioncited by 2
  38. 2023A Generalized Multi-Modal Fusion Detection Frameworkcited by 2

50 most cited of 69 All 69 (JSON)