Research map / Detection and segmentation / 3D detection and driving
MonoGRNet: A General Framework for Monocular 3D Object Detection
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 |
|---|---|---|---|
| add L_Zc instance depth loss (ablation) | MonoGRNet (W) · KITTI val AP3D IoU=0.3 Moderate | AP3D: 28.56 -> 32.33 | Improved |
| add projected 3D center loss L_c (ablation) | MonoGRNet (W) · KITTI val AP3D IoU=0.3 Moderate | AP3D: 32.33 -> 40.59 | Improved |
| add motion consistency loss L_dC (ablation) | MonoGRNet (W) · KITTI val AP3D IoU=0.3 Moderate | AP3D: 40.59 -> 41.19 | Improved |
| add last loss L_a (ablation) | MonoGRNet (W) · KITTI val AP3D IoU=0.3 Moderate | AP3D: 41.19 -> 42.61 | Improved |
| use geometry-guided learning (GeoGL) instead of MinProjErr for 3D location (ablation) | BA x1 orientation · KITTI val AP3D IoU=0.3 Moderate | AP3D: 29.80 -> 41.40 | Improved |
| use object-centric orientation transfer instead of background-aware x1 (ablation) | GeoGL · KITTI val AP3D IoU=0.3 Moderate | AP3D: 41.40 -> 42.61 | Improved |
| use object-centric orientation transfer instead of background-aware x2 (ablation) | GeoGL · KITTI val AP3D IoU=0.3 Moderate | AP3D: 39.16 -> 42.61 | Improved |
| use object-centric transfer instead of background-aware x1 (ablation) | orientation learning · KITTI val AOS IoU=0.3 Moderate | AOS: 80.54 -> 88.78 | Improved |
| enlarge crop with background (BA x2 vs BA x1) (ablation) | orientation learning · KITTI val AOS IoU=0.3 Moderate | AOS: 80.54 -> 62.86 | Hurt |
| use full 3D supervision (MonoGRNet F) instead of weak 2D supervision | MonoGRNet · KITTI val AP3D IoU=0.5 Moderate | AP3D: 21.57 -> 36.20 | Improved |
| use LiDAR supervision during training (Ma et al.) vs mono-only MonoGRNet (F) | monocular 3D detector · KITTI val AP3D IoU=0.5 Moderate | AP3D: 36.20 -> 49.19 | Improved |
Closest papers by meaning
- MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization (AAAI 2019 · similarity 0.95)
- Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection (AAAI 2022 · similarity 0.91)
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.91)
- MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders (NeurIPS 2024 · similarity 0.90)
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (CVPR 2024 · similarity 0.89)
- MonoCD: Monocular 3D Object Detection with Complementary Depths (CVPR 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.
