Research map / Point clouds / Segmentation and detection
OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Clouds
Ziyang Song, Bo Yang
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 dynamic rigid loss (ablation) | OGC · SAPIEN | AP: 35.4 -> 55.6 | Improved |
| add smoothness loss (ablation) | OGC · SAPIEN | AP: 21.8 -> 55.6 | Improved |
| add invariance loss (ablation) | OGC · SAPIEN | AP: 48.9 -> 55.6 | Improved |
| remove dynamic rigid loss (ablation) | OGC · SAPIEN | AP: 91.1 vs 65.0 precision | Mixed |
| iterative optimization from 1 to 2 rounds (ablation) | OGC · SAPIEN | AP: 45.9 -> 55.6 | Improved |
| iterative optimization from 2 to 3 rounds (ablation) | OGC · SAPIEN | AP: 55.6 -> 56.3 | No clear effect |
| input point cloud instead of scene flow (ablation) | OGC · KITTI-SF | AP: 47.3 -> 54.4 | Improved |
| unsupervised OGC vs fully supervised OGC sup | OGC · OGC-DR | AP: 90.7 -> 92.3 | Improved |
| unsupervised OGC vs fully supervised OGC sup | OGC · SAPIEN | AP: 66.1 -> 55.6 | Hurt |
| use estimated object masks to refine scene flow vs FlowStep3D | OGC · KITTI-SF | EPE3D: 10.21 -> 6.72 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- PointRCNN — PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud (CVPR 2019) · better on 0 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Unsupervised 3D Object Segmentation of Point Clouds by Geometry Consistency (TPAMI 2024 · similarity 0.99)
- FreePoint: Unsupervised Point Cloud Instance Segmentation (CVPR 2024 · similarity 0.89)
- AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation (ICLR 2024 · similarity 0.88)
- Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance (CVPR 2024 · similarity 0.87)
- UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes (CVPR 2024 · similarity 0.87)
- Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking (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.
