Research map / Point clouds / Segmentation and detection
Lidar Point Cloud Guided Monocular 3D Object Detection
Liang Peng, Fei Liu, Zhengxu Yu, Senbo Yan, Dan Deng, Zheng Yang, Haifeng Liu, Deng Cai
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 LPCG pseudo labels | MonoGRNet · KITTI val Car moderate | AP3D R40: 7.57 -> 10.06 | Improved |
| add LPCG pseudo labels | M3D-RPN · KITTI val Car moderate | AP3D R40: 11.07 -> 19.61 | Improved |
| add LPCG pseudo labels | RTM3D · KITTI val Car moderate | AP3D R40: 10.06 -> 19.43 | Improved |
| add LPCG pseudo labels | GrooMeD-NMS · KITTI val Car moderate | AP3D R40: 14.32 -> 20.46 | Improved |
| add LPCG pseudo labels | MonoFlex · KITTI test Car moderate | AP3D R40: 13.89 -> 17.80 | Improved |
| add LPCG pseudo labels | M3D-RPN · KITTI test Car moderate | AP3D R40: 9.71 -> 14.82 | Improved |
| use only 100 annotations instead of full 3712 for the LiDAR detector (ablation) | LPCG M3D-RPN · KITTI val Car moderate | AP3D R40: 19.61 -> 15.37 | Hurt |
| use 1000 annotations instead of full 3712 (ablation) | LPCG M3D-RPN · KITTI val Car moderate | AP3D R40: 19.61 -> 19.29 | No clear effect |
| train with 10% labeled plus 90% unlabeled LPCG data instead of 100% labeled | M3D-RPN · Waymo Level 1 overall | 3D mAP: 6.42 -> 6.23 | No clear effect |
| add LPCG unlabeled data to 10% labeled data | M3D-RPN · Waymo Level 1 overall | 3D mAP: 4.14 -> 6.23 | Improved |
| swap PV-RCNN for PointPillars as pseudo-label LiDAR detector (ablation) | LPCG M3D-RPN · KITTI val Car moderate | AP3D R40: 19.61 -> 20.12 | No clear effect |
| increase pseudo-labeled training samples from 100 to 26057 (ablation) | LPCG M3D-RPN · KITTI val Car moderate IoU 0.7 | AP3D R40: 0.21 -> 19.61 | Improved |
Closest papers by meaning
- Training an Open-Vocabulary Monocular 3D Detection Model without 3D Data (NeurIPS 2024 · similarity 0.89)
- iDet3D: Towards Efficient Interactive Object Detection for LiDAR Point Clouds (AAAI 2024 · similarity 0.88)
- Weakly Supervised Monocular 3D Detection with a Single-View Image (CVPR 2024 · similarity 0.88)
- Seg2Box: 3D Object Detection by Point-Wise Semantics Supervision (AAAI 2025 · similarity 0.88)
- Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detection (AAAI 2024 · similarity 0.88)
- LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection (ICLR 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.
