Research map / Point clouds / Segmentation and detection
Weakly Supervised 3D Segmentation via Receptive-Driven Pseudo Label Consistency and Structural Consistency
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 |
|---|---|---|---|
| Use receptive-driven pseudo-label consistency with multi-scale scoring and selection (ablation) | RPSC · S3DIS Area 5, 1pt-c | mIoU (%): 51.4 -> 54.5 | Helped |
| Add semantic structural consistency using labeled-point prototypes (ablation) | RPSC · S3DIS Area 5, 1pt-c | mIoU (%): 51.4 -> 52.7 | Helped |
| Add relation structural consistency between category prototypes (ablation) | RPSC · S3DIS Area 5, 1pt-c | mIoU (%): 51.4 -> 53.8 | Helped |
| Add PLC to a model with SSC but without RSC (ablation) | RPSC · S3DIS Area 5, 1pt-c | mIoU (%): 52.7 -> 55.1 | Helped |
| Add PLC to a model with RSC but without SSC (ablation) | RPSC · S3DIS Area 5, 1pt-c | mIoU (%): 53.8 -> 55.8 | Helped |
| Add SSC to a model with PLC but without RSC (ablation) | RPSC · S3DIS Area 5, 1pt-c | mIoU (%): 54.5 -> 55.1 | Helped |
| Add SSC to a model with RSC but without PLC (ablation) | RPSC · S3DIS Area 5, 1pt-c | mIoU (%): 53.8 -> 54.6 | Helped |
| Add RSC to a model with PLC but without SSC (ablation) | RPSC · S3DIS Area 5, 1pt-c | mIoU (%): 54.5 -> 55.8 | Helped |
| Add RSC to a model with SSC but without PLC (ablation) | RPSC · S3DIS Area 5, 1pt-c | mIoU (%): 52.7 -> 54.6 | Helped |
| Use all three consistency constraints rather than PLC and SSC only (ablation) | RPSC · S3DIS Area 5, 1pt-c | mIoU (%): 55.1 -> 56.3 | Helped |
Closest papers by meaning
- Weakly Supervised Semantic Point Cloud Segmentation: Towards 10x Fewer Labels (CVPR 2020 · similarity 0.92)
- Less Is More: Label Recommendation for Weakly Supervised Point Cloud Semantic Segmentation (AAAI 2024 · similarity 0.91)
- Multi-Modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation (AAAI 2024 · similarity 0.90)
- Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle (CVPR 2024 · similarity 0.90)
- Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation (AAAI 2024 · similarity 0.88)
- Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation (NeurIPS 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.