Research map / Detection and segmentation / 3D detection and driving
Multi-Task Multi-Sensor Fusion for 3D Object Detection
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 image features through point-wise fusion (ablation) | LiDAR-only detector · KITTI car, four-fold cross validation | 3D AP, moderate: +5.21 | Helped |
| add online ground estimation (ablation) | MMF detector with image and point-wise fusion · KITTI car, four-fold cross validation | 3D AP, moderate: +7.14 | Helped |
| add online ground estimation (ablation) | MMF detector with image and point-wise fusion · KITTI car, four-fold cross validation | BEV AP, moderate: +3.77 | Helped |
| add ROI-wise feature fusion and refinement (ablation) | MMF detector with ground estimation · KITTI car, four-fold cross validation | 3D AP, moderate: +8.62 | Helped |
| add depth completion (ablation) | MMF detector with ROI-wise refinement · KITTI car, four-fold cross validation | BEV AP, moderate: +5.16 | Helped |
| add dense point-wise fusion using estimated depth (ablation) | MMF with depth completion · KITTI car, four-fold cross validation | BEV AP, moderate: +5.27 | No clear effect |
| add depth completion supervision (ablation) | ContFuse · TOR4D BEV, bicyclist, AP at IoU 0.5 | AP: 58.0 -> 62.2 | Helped |
| add dense fusion using estimated depth (ablation) | ContFuse with depth completion · TOR4D BEV, vehicle, AP at IoU 0.5 | AP: 95.1 -> 95.7 | Helped |
Closest papers by meaning
- PI-RCNN: An Efficient Multi-Sensor 3D Object Detector with Point-Based Attentive Cont-Conv Fusion Module (AAAI 2020 · similarity 0.88)
- RobuRCDet: Enhancing Robustness of Radar-Camera Fusion in Bird's Eye View for 3D Object Detection (ICLR 2025 · similarity 0.85)
- PromptDet: A Lightweight 3D Object Detection Framework with LiDAR Prompts (AAAI 2025 · similarity 0.85)
- Instance-Aware Multi-Camera 3D Object Detection with Structural Priors Mining and Self-Boosting Learning (AAAI 2024 · similarity 0.85)
- Beyond Virtual Points: Depth-Enhanced LiDAR-only 3D Object Detection with Semi-Supervised Learning (Student Abstract) (AAAI 2025 · similarity 0.85)
- Towards Generalizable Multi-Camera 3D Object Detection via Perspective Rendering (AAAI 2025 · similarity 0.85)
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.