mlsanityData to 14 Oct 2026

MonoDETRNext: Next-Generation Accurate and Efficient Monocular 3D Object Detector

arXiv 2405.15176 ↗First posted 24 May 2024cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Monocular 3D object detection has vast application potential across various fields. DETR-type models have shown remarkable performance in different areas, but there is still considerable room for improvement in monocular 3D detection, especially with the existing DETR-based method, MonoDETR. After addressing the query initialization issues in MonoDETR, we explored several performance enhancement strategies, such as incorporating a more efficient encoder and utilizing a more powerful depth estimator. Ultimately, we proposed MonoDETRNext, a model that comes in two variants based on the choice of depth estimator: MonoDETRNext-E, which prioritizes speed, and MonoDETRNext-A, which focuses on accuracy. We posit that MonoDETRNext establishes a new benchmark in monocular 3D object detection and opens avenues for future research. We conducted an exhaustive evaluation demonstrating the model's superior performance against existing solutions. Notably, MonoDETRNext-A demonstrated a 3.52% improvement in the AP3D metric on the KITTI test benchmark over MonoDETR, while MonoDETRNext-E showed a 2.35% increase. Additionally, the computational efficiency of MonoDETRNext-E slightly exceeds that of its predecessor.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 73 of its 85 references that are in the map. First posted on arXiv 24 May 2024.

Builds on

73 of 85 references.

References · 73

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2020End-to-End Object Detection with Transformerscited by 7,414
  4. 2016Layer Normalizationcited by 5,669
  5. 2022A ConvNet for the 2020scited by 3,579
  6. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  7. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  8. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,319
  9. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  10. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 898
  11. 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 692
  12. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 658
38 more
  1. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
  2. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 573
  3. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 572
  4. 2020HOTA: A Higher Order Metric for Evaluating Multi-Object Trackingcited by 552
  5. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 552
  6. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 533
  7. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 488
  8. 2020Tracking Objects as Pointscited by 483
  9. 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
  10. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 381
  11. 2020Meta Pseudo Labelscited by 374
  12. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 352
  13. 2021XCiT: Cross-Covariance Image Transformerscited by 338
  14. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 336
  15. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 327
  16. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 315
  17. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  18. 2022DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detectioncited by 224
  19. 2020SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimationcited by 204
  20. 2022FUTR3D: A Unified Sensor Fusion Framework for 3D Detectioncited by 194
  21. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 191
  22. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 185
  23. 2019Learning Depth-Guided Convolutions for Monocular 3D Object Detectioncited by 169
  24. 2022Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wildcited by 160
  25. 2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 156
  26. 2020MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationshipscited by 153
  27. 2020RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Drivingcited by 150
  28. 2021Delving into Localization Errors for Monocular 3D Object Detectioncited by 140
  29. 2021Efficient DETR: Improving End-to-End Object Detector with Dense Priorcited by 128
  30. 2021Learning to Track with Object Permanencecited by 119
  31. 2020Rethinking Pseudo-LiDAR Representationcited by 109
  32. 2022MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformercited by 109
  33. 2022Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimationcited by 100
  34. 2022Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignmentcited by 98
  35. 2021AutoShape: Real-Time Shape-Aware Monocular 3D Object Detectioncited by 87
  36. 2022MonoDETR: Depth-guided Transformer for Monocular 3D Object Detectioncited by 86
  37. 2021Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detectioncited by 84
  38. 2021Geometry-based Distance Decomposition for Monocular 3D Object Detectioncited by 84

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Online 3D Multi-Camera Perception through Robust 2D Tracking and Depth-based Late Aggregationcited by 2