Research map / Detection and segmentation / 3D detection and driving
MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization
Zengyi Qin, Jinglu Wang, Yan Lu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use MonoGRNet instead of MF3D | Monocular 3D detection · KITTI val1 car, AP3D IoU=0.7 Moderate | AP3D: 5.69 -> 10.19 | Improved |
| Use MonoGRNet instead of MF3D | Monocular 3D detection · KITTI val1 car, AP3D IoU=0.5 Moderate | AP3D: 29.48 -> 36.97 | Improved |
| Use the fast single-stage 2D detector in MonoGRNet | MonoGRNet · KITTI val1 car, inference | inference time (s/image): 0.12 -> 0.06 | Improved |
| Replace the projected 3D center with the 2D bounding-box center (ablation) | MonoGRNet 3D localization · KITTI 3D localization | horizontal location error (m): 0.27 -> 0.35 | Hurt |
| Replace the projected 3D center with the 2D bounding-box center (ablation) | MonoGRNet 3D localization · KITTI 3D localization | vertical location error (m): 0.09 -> 0.69 | Hurt |
| Regress local corners in a rotated object-centered coordinate frame (ablation) | MonoGRNet local corner regression · KITTI 3D box orientation | orientation error (rad): 0.442 -> 0.251 | Improved |
| Regress corners in the rotated object-centered frame rather than camera coordinates (ablation) | MonoGRNet local corner regression · KITTI 3D bounding-box size | height, width, and length error | No clear effect |
Later papers that compared with this method
5 later accepted papers report MonoGRNet as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- Reinforced Axial Refinement Network for Monocular 3D Object Detection (ECCV 2020 · better on 3 of 3 shared results)
- RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving (ECCV 2020 · better on 2 of 2 shared results)
- MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships (CVPR 2020 · better on 1 of 1 shared result)
- Triangulation Learning Network: From Monocular to Stereo 3D Object Detection (CVPR 2019 · better on 7 of 7 shared results)
- Disentangling Monocular 3D Object Detection (ICCV 2019 · better on 3 of 3 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- MonoGRNet: A General Framework for Monocular 3D Object Detection (TPAMI 2021 · similarity 0.95)
- MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation (CVPR 2021 · similarity 0.89)
- Mono3DVG: 3D Visual Grounding in Monocular Images (AAAI 2024 · similarity 0.89)
- MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders (NeurIPS 2024 · similarity 0.89)
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.88)
- MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
