Research map / Point clouds / Segmentation and detection
Omni-Supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning
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 RFCR to deformable KPConv | Deformable KPConv · ScanNet v2 | mIoU (%): 68.4 -> 70.2 | Helped |
| Add RFCR to SceneEncoder | SceneEncoder · ScanNet v2 | mIoU (%): 62.8 -> 65.9 | Helped |
| Add RFCR to deformable KPConv | Deformable KPConv · S3DIS Area-5 | mIoU (%): 67.1 -> 68.73 | Helped |
| Add RFCR to RandLA | RandLA · S3DIS Area-5 | mIoU (%): 62.42 -> 65.09 | Helped |
| Add RFCR to deformable KPConv | Deformable KPConv · Semantic3D reduced-8 | mIoU (%): 73.1 -> 77.8 | Helped |
| Add RFCR to rigid KPConv | Rigid KPConv · Semantic3D reduced-8 | mIoU (%): 74.6 -> 77.6 | Helped |
| Add gradual RFCR supervision without Feature Densification (ablation) | Deformable KPConv · Semantic3D reduced-8 | mIoU: 73.1 -> 76.0 | Helped |
| Add Feature Densification to RFCR (ablation) | Deformable KPConv + RFCR · Semantic3D reduced-8 | mIoU: 76.0 -> 77.8 | Helped |
| Replace RFCR with nearest-neighbor up-sampling supervision (ablation) | Deformable KPConv + Feature Densification · Semantic3D reduced-8 | mIoU: 77.8 -> 76.2 | Hurt |
| Replace multi-hot RFCCs with one-hot majority-category RFCCs (ablation) | Deformable KPConv + RFCR + Feature Densification · Semantic3D reduced-8 | mIoU: 77.8 -> 76.4 | Hurt |
| Move RFCR and Feature Densification supervision from decoder to encoder (ablation) | Deformable KPConv · Semantic3D reduced-8 | mIoU: 77.8 -> 76.8 | Hurt |
| Remove supervision at scale 5 (ablation) | RFCR + Feature Densification · Semantic3D reduced-8 | mIoU: 77.8 -> 76.6 | Hurt |
Closest papers by meaning
- FreePoint: Unsupervised Point Cloud Instance Segmentation (CVPR 2024 · similarity 0.87)
- ODIN: A Single Model for 2D and 3D Segmentation (CVPR 2024 · similarity 0.86)
- PDF: A Probability-Driven Framework for Open World 3D Point Cloud Semantic Segmentation (CVPR 2024 · similarity 0.86)
- OneFormer3D: One Transformer for Unified Point Cloud Segmentation (CVPR 2024 · similarity 0.86)
- Multi-Modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation (AAAI 2024 · similarity 0.86)
- OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation (CVPR 2024 · similarity 0.86)
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.