Research map / Point clouds / Segmentation and detection
Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation
Tong He, Dong Gong, Zhi Tian, Chunhua Shen
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 focal loss (ablation) | Baseline · S3DIS Area-5 | mPrec: 52.3 -> 55.2 | Improved |
| add focal loss (ablation) | Baseline · S3DIS Area-5 | mRec: 41.4 -> 43.0 | Improved |
| add instance memory M (ablation) | Baseline · S3DIS Area-5 | mPrec: 52.3 -> 58.9 | Improved |
| add instance memory M (ablation) | Baseline · S3DIS Area-5 | mRec: 41.4 -> 47.0 | Improved |
| add instance memory M (ablation) | Baseline · S3DIS Area-5 | oAcc: 86.2 -> 87.7 | Improved |
| add semantic memory C (ablation) | InsMem · S3DIS Area-5 | mPrec: 58.9 -> 60.2 | Improved |
| add semantic memory C (ablation) | InsMem · S3DIS Area-5 | oAcc: 87.7 -> 88.1 | Improved |
| add regularization losses R_ins and R_seg (ablation) | InsMem + SegMem · S3DIS Area-5 | mPrec: 60.2 -> 62.5 | Improved |
| add regularization losses R_ins and R_seg (ablation) | InsMem + SegMem · S3DIS Area-5 | mRec: 47.2 -> 49.0 | Improved |
| increase memory slots per category from 100 to 150 (ablation) | MPNet · S3DIS Area-5 | mPrec: 60.4 -> 62.7 | Improved |
| increase memory slots per category from 150 to 200 (ablation) | MPNet · S3DIS Area-5 | mPrec: 62.7 -> 62.5 | No clear effect |
| use memory-augmented network instead of ASIS KNN fusion | ASIS · S3DIS Area-5 | Overall inference time (ms): 183 -> 165 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SGPN — SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation (CVPR 2018) · better on 3 of 3 shared results
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
- Associatively Segmenting Instances and Semantics in Point Clouds (CVPR 2019 · similarity 0.91)
- Geometry and Uncertainty-Aware 3D Point Cloud Class-Incremental Semantic Segmentation (CVPR 2023 · similarity 0.90)
- Point-MoE: Large-Scale Multi-Dataset Training with Mixture-of-Experts for 3D Semantic Segmentation (ICLR 2026 · similarity 0.90)
- 3D Instance Segmentation via Enhanced Spatial and Semantic Supervision (ICCV 2023 · similarity 0.90)
- DyCo3D: Robust Instance Segmentation of 3D Point Clouds Through Dynamic Convolution (CVPR 2021 · similarity 0.90)
- ISBNet: A 3D Point Cloud Instance Segmentation Network With Instance-Aware Sampling and Box-Aware Dynamic Convolution (CVPR 2023 · 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.
