Research map / Point clouds / Segmentation and detection
PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection
Read the paperCheck 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 point cloud completion and AMS-GNN (ablation) | PointRCNN baseline with PointNet++ · KITTI val, car | 3D mAP: 81.63% -> 84.27%; +2.64% | Helped |
| Add AMS-GNN without point cloud completion (ablation) | PointRCNN baseline with PointNet++ · KITTI val, car | 3D mAP: 81.63% -> 82.54%; ↑0.91 | Helped |
| Add point cloud completion without AMS-GNN (ablation) | PointRCNN baseline with PointNet++ · KITTI val, car | 3D mAP: 81.63% -> 83.18%; ↑1.55 | Helped |
| Add multi-scale graph aggregation (ablation) | Four-layer graph convolution baseline · KITTI val, car | 3D mAP: +0.21% | Helped |
| Add local attention to multi-scale graph aggregation (ablation) | AMS-GNN · KITTI val, car | 3D mAP: +0.62% | Helped |
| Add global attention to multi-scale aggregation and local attention (ablation) | AMS-GNN · KITTI val, car | 3D mAP: +0.16% | Helped |
| Use a graph encoder instead of PointNet in PC-M (ablation) | PC-M · KITTI val, car | 3D mAP: 83.67% -> 84.27%; ↓0.60% | Helped |
| Add the multi-resolution branch (ablation) | PC-M · KITTI val, car | 3D mAP: 83.60% -> 84.27%; ↓0.67% | Helped |
| Preserve original points and add predicted points instead of generating entirely new shapes (ablation) | PC-M · KITTI val, car | 3D mAP: 83.41% -> 84.27%; ↓0.86% | Helped |
| Use PC-RGNN instead of PointRCNN | LiDAR 3D detection · KITTI val, car | AP3D Moderate: 78.63 -> 81.43; +2.80 | Helped |
Closest papers by meaning
- Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud (CVPR 2020 · similarity 0.92)
- VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection (CVPR 2018 · similarity 0.90)
- Multi-View 3D Object Detection Network for Autonomous Driving (CVPR 2017 · similarity 0.90)
- Beyond Virtual Points: Depth-Enhanced LiDAR-only 3D Object Detection with Semi-Supervised Learning (Student Abstract) (AAAI 2025 · similarity 0.88)
- ViKIENet: Towards Efficient 3D Object Detection with Virtual Key Instance Enhanced Network (CVPR 2025 · similarity 0.87)
- GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detection (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.