Research map / Point clouds / Point cloud classification
Structural Relational Reasoning of Point Clouds
Yueqi Duan, Yu Zheng, Jiwen Lu, Jie Zhou, Qi Tian
Check 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 SRN to PointNet++ | PointNet++ · ModelNet40 | classification accuracy (%): 90.6 -> 91.5 | Improved |
| Add SRN to PointNet++ | PointNet++ · ScanNet | classification accuracy (%): 77.1 -> 79.7 | Improved |
| Add SRN to PointNet++ | PointNet++ · ShapeNet Part | mean part IoU (%): 85.1 -> 85.3 | Improved |
| Use geometrical relations only and concatenate features (ablation) | PointNet++ · ModelNet40 | classification accuracy (%): 90.6 -> 91.0 | Improved |
| Use geometrical relations only with residual fusion (ablation) | PointNet++ · ModelNet40 | classification accuracy (%): 90.6 -> 90.7 | Improved |
| Use locational relations only and concatenate features (ablation) | PointNet++ · ModelNet40 | classification accuracy (%): 90.6 -> 91.1 | Improved |
| Use locational relations only with residual fusion (ablation) | PointNet++ · ModelNet40 | classification accuracy (%): 90.6 -> 91.2 | Improved |
| Use both geometrical and locational relations with concatenation (ablation) | PointNet++ · ModelNet40 | classification accuracy (%): 90.6 -> 91.3 | Improved |
| Use both geometrical and locational relations with residual fusion (ablation) | PointNet++ · ModelNet40 | classification accuracy (%): 90.6 -> 91.5 | Improved |
| Use residual fusion instead of concatenation when combining both relation types (ablation) | SRN-PointNet++ · ModelNet40 | classification accuracy (%): 91.3 -> 91.5 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- PointCNN — PointCNN: Convolution On X-Transformed Points (NeurIPS 2018) · better on 1 of 2 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
- Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling (CVPR 2018 · similarity 0.89)
- Relation3D : Enhancing Relation Modeling for Point Cloud Instance Segmentation (CVPR 2025 · similarity 0.87)
- PointCFormer: A Relation-Based Progressive Feature Extraction Network for Point Cloud Completion (AAAI 2025 · similarity 0.87)
- X-3D: Explicit 3D Structure Modeling for Point Cloud Recognition (CVPR 2024 · similarity 0.86)
- Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning (NeurIPS 2025 · similarity 0.86)
- Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding (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.
