Research map / Point clouds / Segmentation and detection
Associatively Segmenting Instances and Semantics 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 |
|---|---|---|---|
| add semantic awareness to the instance branch (ablation) | ASIS with PointNet · S3DIS 6-fold CV | mWCov: 46.3 to 47.4 | Helped |
| add instance fusion to the semantic branch (ablation) | ASIS with PointNet · S3DIS 6-fold CV | mIoU: 49.5 to 50.0 | Helped |
| add instance fusion to the semantic branch (ablation) | ASIS with PointNet · S3DIS 6-fold CV | mWCov: 46.3 to 47.0 | Helped |
| add semantic awareness and instance fusion together (ablation) | ASIS with PointNet · S3DIS 6-fold CV | mIoU: 49.5 to 51.1 | Helped |
| add semantic awareness and instance fusion together (ablation) | ASIS with PointNet · S3DIS 6-fold CV | mWCov: 46.3 to 48.2 | Helped |
| associate semantic awareness and instance fusion end-to-end | ASIS with PointNet · S3DIS 6-fold CV | mWCov: 46.3 to 48.2 | Helped |
| associate semantic awareness and instance fusion end-to-end | ASIS with PointNet · S3DIS 6-fold CV | mIoU: 49.5 to 51.1 | Helped |
| use ASIS instead of SGPN | PointNet instance segmentation · S3DIS 6-fold CV | mWCov: 40.8 to 48.2 | Helped |
| use ASIS instead of PointNet (RePr) | PointNet semantic segmentation · ShapeNet test | mIoU: 83.4 to 84.0 | Helped |
| use ASIS instead of PointNet++* | PointNet++ semantic segmentation · ShapeNet test | mIoU: 84.3 to 85.0 | Helped |
| use ASIS rather than SGPN | instance segmentation · S3DIS Area 5 | inference time: 726 to 205 ms | Helped |
Closest papers by meaning
- Relation3D : Enhancing Relation Modeling for Point Cloud Instance Segmentation (CVPR 2025 · similarity 0.90)
- FreePoint: Unsupervised Point Cloud Instance Segmentation (CVPR 2024 · similarity 0.90)
- Segment Any 3D Object with Language (ICLR 2025 · similarity 0.90)
- OneFormer3D: One Transformer for Unified Point Cloud Segmentation (CVPR 2024 · similarity 0.89)
- Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding (CVPR 2024 · similarity 0.89)
- Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance (CVPR 2024 · similarity 0.89)
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.