Research map / Point clouds / Segmentation and detection
Density-Based Clustering for 3D Object Detection in Point Clouds
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 |
|---|---|---|---|
| Use the cascaded pipeline with foreground filtering, DBSCAN-initialized instance segmentation, and EPN detection | 3D object detection on SUN-RGBD · SUN-RGBD test | mAP (IoU 0.25): 57.7 -> 57.2 | Hurt |
| Filter out points with high Bayesian variance (ablation) | Background-foreground segmentation · SUN-RGBD | accuracy: 75.8 -> 79.1 | Helped |
| Use ideal ground-truth clusters and combine multiple EPN scales (ablation) | EPN object detection · SUN-RGBD test | mAP (IoU 0.25): 57.2 -> 64.9 | Helped |
| Increase DBSCAN ǫ (ablation) | Class-agnostic instance segmentation · SUN-RGBD | mAP | Mixed |
| Use uncertainty estimates for instance segmentation (ablation) | Class-agnostic instance segmentation · SUN-RGBD | prediction variance: 0.02 | No clear effect |
| Limit EPN to K=15 proposals (ablation) | 3D object detection · SUN-RGBD test | average precision | Hurt |
Closest papers by meaning
- 4D Unsupervised Object Discovery (NeurIPS 2022 · similarity 0.89)
- UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classes (NeurIPS 2024 · similarity 0.89)
- Not All Points Are Equal: Learning Highly Efficient Point-Based Detectors for 3D LiDAR Point Clouds (CVPR 2022 · similarity 0.88)
- PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds (CVPR 2023 · similarity 0.88)
- Geometry-Aware 3D Salient Object Detection Network (AAAI 2025 · similarity 0.88)
- FreePoint: Unsupervised Point Cloud Instance Segmentation (CVPR 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.