Research map / Point clouds / Segmentation and detection
Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection
Xin Li, Botian Shi, Yuenan Hou, Xingjiao Wu, Tianlong Ma, Yikang Li, Liang He
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 query fusion mechanism (QFM) (ablation) | Voxel-RCNN baseline · KITTI val (ablation) | AP Easy: 81.34 -> 82.17 | Improved |
| add QFM (ablation) | Voxel-RCNN baseline · KITTI val (ablation) | AP Moderate: 71.76 -> 72.34 | Improved |
| add QFM (ablation) | Voxel-RCNN baseline · KITTI val (ablation) | AP Hard: 67.09 -> 67.73 | Improved |
| add image voxel lifter module (IVLM) on top of QFM (ablation) | HMFI · KITTI val (ablation) | AP Easy: 82.17 -> 82.52 | Improved |
| add IVLM on top of QFM (ablation) | HMFI · KITTI val (ablation) | AP Moderate: 72.34 -> 72.94 | Improved |
| add IVLM on top of QFM (ablation) | HMFI · KITTI val (ablation) | AP Hard: 67.73 -> 68.45 | Improved |
| add voxel feature interaction module (VFIM) on top of QFM and IVLM (ablation) | HMFI · KITTI val (ablation) | AP Easy: 82.52 -> 83.36 | Improved |
| add VFIM on top of QFM and IVLM (ablation) | HMFI · KITTI val (ablation) | AP Moderate: 72.94 -> 73.89 | Improved |
| add VFIM on top of QFM and IVLM (ablation) | HMFI · KITTI val (ablation) | AP Hard: 68.45 -> 68.98 | Improved |
| full HMFI (QFM, IVLM, VFIM) versus Voxel-RCNN baseline | HMFI · KITTI val (ablation) | AP Moderate: 71.76 -> 73.89 | Improved |
| HMFI versus baseline on Waymo | Voxel-RCNN baseline · Waymo Open Dataset val | Vehicle AP L1: 66.46 -> 68.34 | Improved |
| HMFI versus baseline on Waymo | Voxel-RCNN baseline · Waymo Open Dataset val | Pedestrian AP L2: 62.74 -> 64.91 | Improved |
Closest papers by meaning
- MSMDFusion: Fusing LiDAR and Camera at Multiple Scales With Multi-Depth Seeds for 3D Object Detection (CVPR 2023 · similarity 0.91)
- CCF: Complementary Collaborative Fusion for Domain Generalized Multi-Modal 3D Object Detection (CVPR 2026 · similarity 0.90)
- Multi-Modal 3D Object Detection in Autonomous Driving: A Survey (IJCV 2023 · similarity 0.90)
- Deformable Feature Aggregation for Dynamic Multi-modal 3D Object Detection (ECCV 2022 · similarity 0.90)
- SSLFusion: Scale and Space Aligned Latent Fusion Model for Multimodal 3D Object Detection (AAAI 2025 · similarity 0.88)
- Voxel or Pillar: Exploring Efficient Point Cloud Representation for 3D Object Detection (AAAI 2024 · 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.
