mlsanityData to 7 Oct 2026

IoU Loss for 2D/3D Object Detection

arXiv 1908.03851 ↗First posted 11 Aug 2019cs.CVcited by 128

Not on the map. Why?

Abstract (arXiv)

In 2D/3D object detection task, Intersection-over-Union (IoU) has been widely employed as an evaluation metric to evaluate the performance of different detectors in the testing stage. However, during the training stage, the common distance loss (eg, L1 or L2) is often adopted as the loss function to minimize the discrepancy between the predicted and ground truth Bounding Box (Bbox). To eliminate the performance gap between training and testing, the IoU loss has been introduced for 2D object detection in citeyu2016unitbox and citerezatofighi2019generalized. Unfortunately, all these approaches only work for axis-aligned 2D Bboxes, which cannot be applied for more general object detection task with rotated Bboxes. To resolve this issue, we investigate the IoU computation for two rotated Bboxes first and then implement a unified framework, IoU loss layer for both 2D and 3D object detection tasks. By integrating the implemented IoU loss into several state-of-the-art 3D object detectors, consistent improvements have been achieved for both bird-eye-view 2D detection and point cloud 3D detection on the public KITTI benchmark.

Key facts. Cited by 128 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 27; 2022: 32; 2023: 23; 2024: 23; 2025: 18; 2026: 5.

128 papers.

Sort:

By area:

  1. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  2. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  3. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
  4. 2025YOLOv12: Attention-Centric Real-Time Object Detectorscited by 300
  5. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  6. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 192
  7. 2021ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detectioncited by 157
  8. 2021Delving into Localization Errors for Monocular 3D Object Detectioncited by 138
  9. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  10. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  11. 2021SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloudcited by 119
  12. 2024PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AIcited by 116
38 more
  1. 2021RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detectioncited by 115
  2. 2021Improving 3D Object Detection with Channel-wise Transformercited by 108
  3. 20213D Object Detection for Autonomous Driving: A Surveycited by 106
  4. 2021FCAF3D: Fully Convolutional Anchor-Free 3D Object Detectioncited by 97
  5. 2024LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Modelscited by 94
  6. 2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 93
  7. 2021FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detectioncited by 92
  8. 2022SWFormer: Sparse Window Transformer for 3D Object Detection in Point Cloudscited by 92
  9. 2021AutoShape: Real-Time Shape-Aware Monocular 3D Object Detectioncited by 87
  10. 2023Virtual Sparse Convolution for Multimodal 3D Object Detectioncited by 81
  11. 2022The KFIoU Loss for Rotated Object Detectioncited by 73
  12. 2021LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detectorcited by 69
  13. 2021Behind the Curtain: Learning Occluded Shapes for 3D Object Detectioncited by 58
  14. 2022AO2-DETR: Arbitrary-Oriented Object Detection Transformercited by 55
  15. 2021VPFNet: Improving 3D Object Detection with Virtual Point based LiDAR and Stereo Data Fusioncited by 48
  16. 2021HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detectioncited by 47
  17. 2022NeRF-RPN: A general framework for object detection in NeRFscited by 46
  18. 2023Segment Anything Model for Medical Images?cited by 39
  19. 2022Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalizationcited by 36
  20. 2024Towards Vision-Language Geo-Foundation Model: A Surveycited by 36
  21. 2022CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detectioncited by 30
  22. 2021FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detectioncited by 29
  23. 2023Uni3DETR: Unified 3D Detection Transformercited by 26
  24. 2022DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detectioncited by 25
  25. 2022Rethinking IoU-based Optimization for Single-stage 3D Object Detectioncited by 19
  26. 2023Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation APIcited by 18
  27. 2021BADet: Boundary-Aware 3D Object Detection from Point Cloudscited by 17
  28. 2021Gaussian Bounding Boxes and Probabilistic Intersection-over-Union for Object Detectioncited by 17
  29. 2022Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Cloudscited by 17
  30. 2021IAFA: Instance-aware Feature Aggregation for 3D Object Detection from a Single Imagecited by 15
  31. 2023Rethinking Boundary Discontinuity Problem for Oriented Object Detectioncited by 15
  32. 2023ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detectioncited by 14
  33. 2025CasaGPT: Cuboid Arrangement and Scene Assembly for Interior Designcited by 14
  34. 2021SCPM-Net: An Anchor-free 3D Lung Nodule Detection Network using Sphere Representation and Center Points Matchingcited by 12
  35. 2023LiDAR-CS Dataset: LiDAR Point Cloud Dataset with Cross-Sensors for 3D Object Detectioncited by 12
  36. 2022Multi-Sem Fusion: Multimodal Semantic Fusion for 3D Object Detectioncited by 11
  37. 2022A Survey of Robust 3D Object Detection Methods in Point Cloudscited by 10
  38. 2022Multimodal Transformer for Automatic 3D Annotation and Object Detectioncited by 10

50 most cited of 128 All 128 (JSON)