Research map / Detection and segmentation / 3D detection and driving
Semi-Supervised Monocular 3D Object Detection by Multi-View Consistency
Qing Lian, Yanbo Xu, Weilong Yao, Yingcong Chen, Tong Zhang
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 box-level consistency regularization (ablation) | MVC-MonoDet (stereo) · KITTI val Car 100% | 3D AP Moderate: 16.32 -> 17.56 | Improved |
| add object-level consistency regularization (ablation) | MVC-MonoDet (stereo) · KITTI val Car 100% | 3D AP Moderate: 16.32 -> 17.85 | Improved |
| combine box-level and object-level regularization (ablation) | MVC-MonoDet (stereo) · KITTI val Car 100% | 3D AP Moderate: 17.85 -> 18.63 | Improved |
| add box-level consistency regularization (ablation) | MVC-MonoDet (video) · KITTI val Car 100% | 3D AP Moderate: 16.32 -> 17.01 | Improved |
| add object-level consistency regularization (ablation) | MVC-MonoDet (video) · KITTI val Car 100% | 3D AP Moderate: 16.32 -> 16.75 | Mixed |
| combine box-level and object-level regularization (ablation) | MVC-MonoDet (video) · KITTI val Car 100% | 3D AP Moderate: 17.01 -> 17.34 | Improved |
| use stereo instead of video as unlabeled multi-view data (ablation) | MVC-MonoDet · KITTI val Car 100% | 3D AP Moderate: 17.34 -> 18.63 | Improved |
| add semi-supervised multi-view consistency instead of multi-task depth supervision (ablation) | Baseline detector (stereo) · KITTI val Car 100% | 3D AP Moderate: 17.21 -> 18.63 | Improved |
| use 10% labeled data with consistency regularization (ablation) | MVC-MonoDet (video) · KITTI val Car 10% | 3D AP Moderate: 7.25 -> 7.96 | No clear effect |
| add MVC-MonoDet semi-supervised training with stereo (ablation) | Baseline · KITTI val Car 50% vs 100% labeled | 3D AP Moderate: 16.40 vs 16.32 | Improved |
| add MVC-MonoDet video training on nuScenes (ablation) | Baseline · nuScenes val 10% labeled | mAP: 15.9 -> 18.8 | Improved |
| add MVC-MonoDet video training on nuScenes (ablation) | Baseline · nuScenes val 100% labeled | mAP: 33.2 -> 34.9 | Improved |
Closest papers by meaning
- Weakly Supervised Monocular 3D Object Detection by Spatial-Temporal View Consistency (TPAMI 2024 · similarity 0.90)
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.89)
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (CVPR 2024 · similarity 0.88)
- MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders (NeurIPS 2024 · similarity 0.88)
- MonoCD: Monocular 3D Object Detection with Complementary Depths (CVPR 2024 · similarity 0.88)
- Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection (NeurIPS 2024 · similarity 0.88)
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.
