mlsanityData to 14 Oct 2026

ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape

arXiv 1812.02781 ↗First posted 6 Dec 2018cs.CVcited by 123

Not on the map. Why?

Abstract (arXiv)

We present a deep learning method for end-to-end monocular 3D object detection and metric shape retrieval. We propose a novel loss formulation by lifting 2D detection, orientation, and scale estimation into 3D space. Instead of optimizing these quantities separately, the 3D instantiation allows to properly measure the metric misalignment of boxes. We experimentally show that our 10D lifting of sparse 2D Regions of Interests (RoIs) achieves great results both for 6D pose and recovery of the textured metric geometry of instances. This further enables 3D synthetic data augmentation via inpainting recovered meshes directly onto the 2D scenes. We evaluate on KITTI3D against other strong monocular methods and demonstrate that our approach doubles the AP on the 3D pose metrics on the official test set, defining the new state of the art.

Key facts. Cited by 123 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 42; 2022: 31; 2023: 28; 2024: 9; 2025: 11; 2026: 2.

123 papers.

Sort:

By area:

  1. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 447
  2. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 327
  3. 2022Cross-view Transformers for real-time Map-view Semantic Segmentationcited by 264
  4. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 249
  5. 2022Language-Grounded Indoor 3D Semantic Segmentation in the Wildcited by 246
  6. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  7. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 185
  8. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 178
  9. 2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 156
  10. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  11. 2021Delving into Localization Errors for Monocular 3D Object Detectioncited by 140
  12. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
38 more
  1. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  2. 2022MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queriescited by 91
  3. 2021SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimationcited by 88
  4. 2021AutoShape: Real-Time Shape-Aware Monocular 3D Object Detectioncited by 87
  5. 2021Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detectioncited by 84
  6. 2021CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Cloudscited by 84
  7. 2021Geometry-based Distance Decomposition for Monocular 3D Object Detectioncited by 84
  8. 2021Monocular 3D Object Detection: An Extrinsic Parameter Free Approachcited by 69
  9. 2021Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detectioncited by 67
  10. 2021GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detectioncited by 66
  11. 20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66
  12. 2022Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detectioncited by 46
  13. 2024Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimationcited by 43
  14. 2022DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detectioncited by 39
  15. 2022MonoGround: Detecting Monocular 3D Objects from the Groundcited by 37
  16. 2023Learning Occupancy for Monocular 3D Object Detectioncited by 36
  17. 2021The Devil is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detectioncited by 34
  18. 2022Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimationcited by 34
  19. 2023MonoNeRD: NeRF-like Representations for Monocular 3D Object Detectioncited by 33
  20. 2021Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overviewcited by 31
  21. 2022MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detectioncited by 30
  22. 2022CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detectioncited by 30
  23. 2021Lidar Point Cloud Guided Monocular 3D Object Detectioncited by 29
  24. 2023Open-vocabulary object 6D pose estimationcited by 29
  25. 2022OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detectioncited by 24
  26. 2022TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimationcited by 23
  27. 2023MonoGAE: Roadside Monocular 3D Object Detection with Ground-Aware Embeddingscited by 22
  28. 2024OmniNOCS: A unified NOCS dataset and model for 3D lifting of 2D objectscited by 22
  29. 2021MonoGRNet: A General Framework for Monocular 3D Object Detectioncited by 20
  30. 2021Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detectioncited by 20
  31. 2023MonoLSS: Learnable Sample Selection For Monocular 3D Detectioncited by 19
  32. 2022WeakM3D: Towards Weakly Supervised Monocular 3D Object Detectioncited by 18
  33. 2023Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistencycited by 18
  34. 2023MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformercited by 18
  35. 2022Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Cloudscited by 17
  36. 2023HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimationcited by 17
  37. 2021MonoCInIS: Camera Independent Monocular 3D Object Detection using Instance Segmentationcited by 16
  38. 2021CloudAAE: Learning 6D Object Pose Regression with On-line Data Synthesis on Point Cloudscited by 15

50 most cited of 123 All 123 (JSON)