mlsanityData to 14 Oct 2026

MAGneT-3D: Monocular and Domain-Generalizable Temporal 3D Detection

arXiv 2608.14282 ↗First posted 14 Aug 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Monocular temporal 3D detection aims to detect objects in 3D, given a monocular video. Query-based 3D detectors unify detection and cross-view association, but their learnable queries fit the spatial distribution of the training data (e.g., field-of-view). We show that this issue is especially severe when these models are applied to monocular video, hindering generalization to unseen datasets and environments. To address this limitation, we introduce MAGneT-3D, the first method for domain-generalized monocular temporal 3D object detection. Instead of relying on static learnable queries, we propose a Domain-Robust Anchor Generator (DRAG) approach that adaptively derives 3D proposals during inference. To further enable domain generalization, we propose a Temporal Refinement and Identity Merging (TRIM) strategy, reducing dependence on specific 3D proposals. To enable comprehensive domain-generalization evaluation, we establish a cross-dataset benchmark spanning nuScenes, Waymo, Lyft, and ONCE. Under zero-shot domain shifts, MAGneT-3D outperforms all baselines, improving NDS from 12.1% to 18.6% while also increasing in-domain accuracy.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 60 of its 71 references that are in the map. First posted on arXiv 14 Aug 2026.

Builds on

60 of 71 references.

References · 60

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  3. 2020Supervised Contrastive Learningcited by 2,829
  4. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  5. 2019Objects as Pointscited by 1,175
  6. 2020In Search of Lost Domain Generalizationcited by 1,054
  7. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,044
  8. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 713
  9. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 658
  10. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 552
  11. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 466
  12. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 447
38 more
  1. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  2. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 352
  3. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 341
  4. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 336
  5. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 327
  6. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 315
  7. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  8. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  9. 2020One Thousand and One Hours: Self-driving Motion Prediction Datasetcited by 240
  10. 2022DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detectioncited by 224
  11. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 222
  12. 2021One Million Scenes for Autonomous Driving: ONCE Datasetcited by 218
  13. 2020SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimationcited by 204
  14. 2018Orthographic Feature Transform for Monocular 3D Object Detectioncited by 202
  15. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 162
  16. 2020CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detectioncited by 161
  17. 2022Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wildcited by 160
  18. 2020Kinematic 3D Object Detection in Monocular Videocited by 116
  19. 2023Sparse4D v2: Recurrent Temporal Fusion with Sparse Modelcited by 93
  20. 2023CLIP the Gap: A Single Domain Generalization Approach for Object Detectioncited by 87
  21. 2024RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detectioncited by 82
  22. 2021Monocular Quasi-Dense 3D Object Trackingcited by 81
  23. 2022Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Taskcited by 81
  24. 2023Far3D: Expanding the Horizon for Surround-view 3D Object Detectioncited by 70
  25. 2023Sparse4D v3: Advancing End-to-End 3D Detection and Trackingcited by 70
  26. 20213D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detectioncited by 43
  27. 2024MonoCD: Monocular 3D Object Detection with Complementary Depthscited by 39
  28. 2023Learning Occupancy for Monocular 3D Object Detectioncited by 36
  29. 2023Towards Domain Generalization for Multi-view 3D Object Detection in Bird-Eye-Viewcited by 27
  30. 2022DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detectioncited by 25
  31. 2024The RoboDrive Challenge: Drive Anytime Anywhere in Any Conditioncited by 23
  32. 2022Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Trainingcited by 22
  33. 2024MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priorscited by 22
  34. 2022Focal-PETR: Embracing Foreground for Efficient Multi-Camera 3D Object Detectioncited by 19
  35. 2023MonoLSS: Learnable Sample Selection For Monocular 3D Detectioncited by 19
  36. 2023MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformercited by 18
  37. 2024Unified Domain Generalization and Adaptation for Multi-View 3D Object Detectioncited by 13
  38. 2024CARLA Drone: Monocular 3D Object Detection from a Different Perspectivecited by 12

50 most cited of 60 All 60 (JSON)

Built on by

Not cited yet.