Research map / Detection and segmentation / 3D detection and driving
CoGoal3D: Collaborative 3D Object Detection with 3D-Aware Fusion and Refinement
Zhihao Yang, Zhiyu Xiang, Peng Xu, Tianyu Pu, Kai Wang, Eryun Liu, Dongping Zhang, Yong Ding
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 MCDA data augmentation (ablation) | CoGoal3D · DAIR-V2X val | 3D AP@0.7: 33.27 -> 40.85 | Improved |
| add 3D-AGF module (ablation) | CoGoal3D · DAIR-V2X val | 3D AP@0.7: 40.85 -> 42.66 | Improved |
| add second-stage RCNN refinement (ablation) | CoGoal3D · DAIR-V2X val | 3D AP@0.7: 42.66 -> 48.28 | Improved |
| add RGLR reconstruction-guided refinement (ablation) | CoGoal3D · DAIR-V2X val | 3D AP@0.7: 48.28 -> 50.55 | Improved |
| add 3D position encoding (ablation) | CoGoal3D · DAIR-V2X val | 3D AP@0.7: 46.70 -> 50.55 | Improved |
| add ground truth optimization (ablation) | CoGoal3D · DAIR-V2X val | 3D AP@0.7: 49.57 -> 50.55 | Improved |
| add GTO when 3D PE is absent (ablation) | CoGoal3D · DAIR-V2X val | 3D AP@0.7: 46.70 -> 46.99 | Hurt |
| replace DPTP with MCDA augmentation (ablation) | CoGoal3D Stage1 · DAIR-V2X val | 3D AP@0.7: 38.48 -> 42.66 | Improved |
| apply DPTP rotation and scaling on top of flipping (ablation) | CoGoal3D Stage1 · DAIR-V2X val | 3D AP@0.5: 71.26 -> 70.02 | Hurt |
| add MCDA rotation to flipping (ablation) | CoGoal3D Stage1 · DAIR-V2X val | 3D AP@0.5: 72.57 -> 73.29 | Improved |
| replace DPTP with MCDA augmentation (ablation) | DI-V2X · DAIR-V2X val | 3D AP@0.7: 39.24 -> 42.54 | Improved |
| replace DPTP with MCDA augmentation (ablation) | DSRC · DAIR-V2X val | 3D AP@0.7: 36.08 -> 40.66 | Improved |
Closest papers by meaning
- DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detection (AAAI 2024 · similarity 0.89)
- IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection (CVPR 2024 · similarity 0.88)
- SparseAlign: a Fully Sparse Framework for Cooperative Object Detection (CVPR 2025 · similarity 0.87)
- Towards Generalizable Multi-Camera 3D Object Detection via Perspective Rendering (AAAI 2025 · similarity 0.87)
- ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images (NeurIPS 2024 · similarity 0.87)
- CorrBEV: Multi-View 3D Object Detection by Correlation Learning with Multi-modal Prototypes (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.
