Research map / Detection and segmentation / 3D detection and driving
M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
Garrick Brazil, Xiaoming Liu
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 |
|---|---|---|---|
| add 3D->2D post-optimization of orientation (ablation) | M3D-RPN · KITTI val1 car Mod | AP_BEV: 12.99 -> 17.47 | Improved |
| add 3D->2D post-optimization of orientation (ablation) | M3D-RPN · KITTI val1 car Mod | AP_3D: 10.99 -> 15.08 | Improved |
| add 3D->2D post-optimization of orientation (ablation) | M3D-RPN · KITTI val1 car Mod | runtime (ms): 118 -> 128 | Hurt |
| add depth-aware convolution with b=32 bins (with post-opt) (ablation) | M3D-RPN · KITTI val1 car Mod | AP_BEV: 17.47 -> 21.18 | Improved |
| add depth-aware convolution with b=32 bins (with post-opt) (ablation) | M3D-RPN · KITTI val1 car Mod | AP_3D: 15.08 -> 17.06 | Improved |
| add depth-aware convolution with b=32 bins (with post-opt) (ablation) | M3D-RPN · KITTI val1 car Mod | AP_2D: 82.16 -> 83.67 | Improved |
| add depth-aware convolution with b=1 bin (two global streams) (ablation) | M3D-RPN · KITTI val1 car Mod | AP_3D: 15.08 -> 12.87 | Hurt |
| add depth-aware convolution with b=4 bins (ablation) | M3D-RPN · KITTI val1 car Mod | AP_3D: 15.08 -> 14.46 | Hurt |
| add depth-aware convolution with b=4 bins (ablation) | M3D-RPN · KITTI val1 car Mod | AP_BEV: 17.47 -> 19.14 | Improved |
| add depth-aware convolution with b=8 bins (ablation) | M3D-RPN · KITTI val1 car Mod | AP_3D: 15.08 -> 16.04 | Improved |
| increase bins from b=8 to b=32 (ablation) | M3D-RPN · KITTI val1 car Mod | AP_3D: 16.04 -> 17.06 | Improved |
| increase bins b from 1 to 32 (ablation) | M3D-RPN · KITTI val1 car Mod | runtime (ms): 133 -> 161 | Hurt |
Later papers that compared with this method
15 later accepted papers report M3D-RPN as a baseline in their results tables; 14 of them report a better number on most of the results they share with it.
- CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection (ECCV 2022 · better on 2 of 2 shared results)
- Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection (ECCV 2022 · better on 1 of 1 shared result)
- Gated3D: Monocular 3D Object Detection From Temporal Illumination Cues (ICCV 2021 · better on 11 of 12 shared results)
- The Devil Is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection (ICCV 2021 · better on 5 of 5 shared results)
- Geometry-Based Distance Decomposition for Monocular 3D Object Detection (ICCV 2021 · better on 5 of 5 shared results)
- Categorical Depth Distribution Network for Monocular 3D Object Detection (CVPR 2021 · better on 2 of 2 shared results)
- Delving Into Localization Errors for Monocular 3D Object Detection (CVPR 2021 · better on 1 of 1 shared result)
- Monocular 3D Object Detection: An Extrinsic Parameter Free Approach (CVPR 2021 · better on 1 of 1 shared result)
7 more not listed.
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
- Monocular 3D Object Detection for Autonomous Driving (CVPR 2016 · similarity 0.92)
- 3D Object Proposals Using Stereo Imagery for Accurate Object Class Detection (TPAMI 2017 · similarity 0.91)
- Multi-View 3D Object Detection Network for Autonomous Driving (CVPR 2017 · similarity 0.91)
- Accurate Monocular 3D Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving (ICCV 2019 · similarity 0.90)
- MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection (ICCV 2023 · similarity 0.90)
- Geometry-Guided Domain Generalization for Monocular 3D Object Detection (AAAI 2024 · similarity 0.89)
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.
