Research map / Detection and segmentation / 3D detection and driving
OA-DET3D: Embedding Object Awareness As A General Plug-in for Multi-Camera 3D Object Detection
Xiaomeng Chu, Jiajun Deng, Jianmin Ji, Yu Zhang, Houqiang Li, Yanyong 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 object-level depth supervision (ablation) | BEVDet-T · nuScenes val | mAP: 31.2 -> 32.6 | Improved |
| add foreground pseudo-3D features (ablation) | OA-BEVDet-T · nuScenes val | mAP: 32.6 -> 33.8 | Improved |
| add depth deformable cross-attention feature integration (ablation) | OA-BEVDet-T · nuScenes val | mAP: 33.8 -> 34.2 | Improved |
| use deformable transformer fusion instead of concatenation (ablation) | OA-BEVDet-T · nuScenes val | mAP: 33.0 -> 34.2 | Improved |
| use deformable transformer fusion instead of addition (ablation) | OA-BEVDet-T · nuScenes val | NDS: 39.9 -> 41.1 | Improved |
| use diagonal multi-point slicing instead of center point diffusion (ablation) | OA-BEVFormer · nuScenes val | mAP: 40.7 -> 40.8 | No clear effect |
| add 2D detection (vs without) (ablation) | OA-BEVDet · nuScenes val | mAP: 31.5 -> 34.2 | Improved |
| replace predicted 2D boxes with 2D ground-truth boxes (ablation) | OA-BEVDet · nuScenes val | mAP: 34.2 -> 36.2 | Improved |
| add OA-DET3D at lower input resolution 704x256 | BEVDet · nuScenes val | mAP: 30.2 -> 34.2 | Improved |
| add OA-DET3D at input resolution 1056x384 | BEVDet · nuScenes val | mAP: 33.3 -> 36.0 | Improved |
| add OA-DET3D in night scenes | BEVDet · nuScenes val night | mAP: 13.4 -> 15.6 | Improved |
| add OA-DET3D in rainy scenes | BEVDet · nuScenes val rainy | mAP: 32.4 -> 35.5 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- BEVFormer — BEVFormer: Learning Bird’s-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers (ECCV 2022) · better on 2 of 2 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
- Towards Generalizable Multi-Camera 3D Object Detection via Perspective Rendering (AAAI 2025 · similarity 0.90)
- Training an Open-Vocabulary Monocular 3D Detection Model without 3D Data (NeurIPS 2024 · similarity 0.89)
- GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object Detection (AAAI 2025 · similarity 0.88)
- ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images (NeurIPS 2024 · similarity 0.88)
- CorrBEV: Multi-View 3D Object Detection by Correlation Learning with Multi-modal Prototypes (CVPR 2025 · similarity 0.88)
- Instance-Aware Multi-Camera 3D Object Detection with Structural Priors Mining and Self-Boosting Learning (AAAI 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.
