Research map / Point clouds / Segmentation and detection
Point Cloud Segmentation of Integrated Circuits Package Substrates Surface Defects Using Causal Inference: Dataset Construction and Methodology
Bingyang Guo, Qiang Zuo, Ruiyun Yu
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 Structural Refine (transformer group encoder instead of MLP) (ablation) | CINet baseline · CPS3D-Seg ablation | mIoU: 0.6832 -> 0.7576 | Improved |
| add Quality Assessment module (GMM over quality metrics) (ablation) | CINet baseline · CPS3D-Seg ablation | mIoU: 0.6832 -> 0.7682 | Improved |
| add mapping attention detection module (ablation) | CINet baseline · CPS3D-Seg ablation | mIoU: 0.6832 -> 0.7891 | Improved |
| combine SR, QA and MAD (ablation) | CINet · CPS3D-Seg ablation | mIoU: 0.7891 (best single) -> 0.8544 | Improved |
| use density, uniformity and integrity together in QA (ablation) | CINet · CPS3D-Seg QA ablation | mIoU: 0.8012-0.8098 (single) -> 0.8544 | Improved |
| use two QA metrics instead of one (ablation) | CINet · CPS3D-Seg QA ablation | mIoU: 0.8098 -> 0.8231 | Improved |
| use CINet vs best prior method PTV3 | CINet · CPS3D-Seg | mIoU: 0.8204 -> 0.8544 | Improved |
| use Mamba-based backbones vs transformer/CNN | Point-cloud segmenters · CPS3D-Seg | mIoU: 0.8204 (PTV3) vs 0.7494 (PointMamba) | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- OneFormer3D — OneFormer3D: One Transformer for Unified Point Cloud Segmentation (CVPR 2024) · better on 1 of 1 shared result
- PointMamba — PointMamba: A Simple State Space Model for Point Cloud Analysis (NeurIPS 2024) · better on 1 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
- SpelsNet: Surface Primitive Elements Segmentation by B-Rep Graph Structure Supervision (NeurIPS 2024 · similarity 0.83)
- Towards Generalizable 3D Anomaly Detection via Relational Inconsistency Modeling (NeurIPS 2026 · similarity 0.82)
- SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation (NeurIPS 2025 · similarity 0.82)
- 3CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised Anomaly Detection (AAAI 2025 · similarity 0.81)
- X-3D: Explicit 3D Structure Modeling for Point Cloud Recognition (CVPR 2024 · similarity 0.81)
- Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detection (NeurIPS 2025 · similarity 0.81)
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.
