mlsanityData to 14 Oct 2026

MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models

arXiv 2503.13743 ↗First posted 17 Mar 2025cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

We tackle the problem of monocular 3D object detection across different sensors, environments, and camera setups. In this paper, we introduce a novel unsupervised domain adaptation approach, MonoCT, that generates highly accurate pseudo labels for self-supervision. Inspired by our observation that accurate depth estimation is critical to mitigating domain shifts, MonoCT introduces a novel Generalized Depth Enhancement (GDE) module with an ensemble concept to improve depth estimation accuracy. Moreover, we introduce a novel Pseudo Label Scoring (PLS) module by exploring inner-model consistency measurement and a Diversity Maximization (DM) strategy to further generate high-quality pseudo labels for self-training. Extensive experiments on six benchmarks show that MonoCT outperforms existing SOTA domain adaptation methods by large margins (~21% minimum for AP Mod.) and generalizes well to car, traffic camera and drone views.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 48 of its 60 references that are in the map. First posted on arXiv 17 Mar 2025.

Builds on

48 of 60 references.

References · 48

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  3. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  4. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  5. 2017Deep Layer Aggregationcited by 436
  6. 2018The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systemscited by 277
  7. 2022DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detectioncited by 273
  8. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 185
  9. 2022Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wildcited by 160
  10. 2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 156
  11. 2020RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Drivingcited by 150
  12. 2019The inD Dataset: A Drone Dataset of Naturalistic Road User Trajectories at German Intersectionscited by 137
36 more
  1. 2023V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecastingcited by 114
  2. 2022Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Taskcited by 81
  3. 2022LargeKernel3D: Scaling up Kernels in 3D Sparse CNNscited by 72
  4. 2021Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detectioncited by 67
  5. 2023FocalFormer3D : Focusing on Hard Instance for 3D Object Detectioncited by 58
  6. 2019Physics-Based Rendering for Improving Robustness to Raincited by 49
  7. 2022DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detectioncited by 48
  8. 2022Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detectioncited by 46
  9. 2024MonoCD: Monocular 3D Object Detection with Complementary Depthscited by 39
  10. 2022MonoGround: Detecting Monocular 3D Objects from the Groundcited by 37
  11. 2019Precise Synthetic Image and LiDAR (PreSIL) Dataset for Autonomous Vehicle Perceptioncited by 29
  12. 2022A Lightweight and Detector-free 3D Single Object Tracker on Point Cloudscited by 23
  13. 2022Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detectioncited by 23
  14. 2022Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Trainingcited by 22
  15. 2023MonoPGC: Monocular 3D Object Detection with Pixel Geometry Contextscited by 21
  16. 2023MonoLSS: Learnable Sample Selection For Monocular 3D Detectioncited by 19
  17. 2023CoBEV: Elevating Roadside 3D Object Detection with Depth and Height Complementaritycited by 18
  18. 2023Scan2LoD3: Reconstructing semantic 3D building models at LoD3 using ray casting and Bayesian networkscited by 17
  19. 2023MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaptation in 3D Object Detectioncited by 14
  20. 2023MS3D: Leveraging Multiple Detectors for Unsupervised Domain Adaptation in 3D Object Detectioncited by 12
  21. 2024UADA3D: Unsupervised Adversarial Domain Adaptation for 3D Object Detection with Sparse LiDAR and Large Domain Gapscited by 12
  22. 2024CARLA Drone: Monocular 3D Object Detection from a Different Perspectivecited by 12
  23. 2020VPC-Net: Completion of 3D Vehicles from MLS Point Cloudscited by 11
  24. 2022Viewer-Centred Surface Completion for Unsupervised Domain Adaptation in 3D Object Detectioncited by 10
  25. 2024WARM-3D: A Weakly-Supervised Sim2Real Domain Adaptation Framework for Roadside Monocular 3D Object Detectioncited by 9
  26. 2023Large Car-following Data Based on Lyft level-5 Open Dataset: Following Autonomous Vehicles vs. Human-driven Vehiclescited by 8
  27. 2024SOAP: Cross-sensor Domain Adaptation for 3D Object Detection Using Stationary Object Aggregation Pseudo-labellingcited by 8
  28. 2024Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detectioncited by 7
  29. 2022Towards Model Generalization for Monocular 3D Object Detectioncited by 6
  30. 2024STAL3D: Unsupervised Domain Adaptation for 3D Object Detection via Collaborating Self-Training and Adversarial Learningcited by 6
  31. 2022BEVUDA: Multi-geometric Space Alignments for Domain Adaptive BEV 3D Object Detectioncited by 5
  32. 2022Depth Is All You Need for Monocular 3D Detectioncited by 4
  33. 2023SCP: Scene Completion Pre-training for 3D Object Detectioncited by 3
  34. 2024MOSE: Boosting Vision-based Roadside 3D Object Detection with Scene Cuescited by 3
  35. 2023MonoTDP: Twin Depth Perception for Monocular 3D Object Detection in Adverse Scenescited by 2
  36. 2024Fully Test-Time Adaptation for Monocular 3D Object Detectioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detectioncited by 1
  2. 2026MAGneT-3D: Monocular and Domain-Generalizable Temporal 3D Detectioncited by 0