Research map / Point clouds / Shape and surface completion
Detail Preserved Point Cloud Completion via Separated Feature Aggregation
Wenxiao Zhang, Qingan Yan, Chunxia Xiao
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 RFA separated feature aggregation (ablation) | NWoSFA · ShapeNet known categories | Chamfer distance: 8.74 -> 8.06 | Improved |
| add GLFA separated feature aggregation (ablation) | NWoSFA · ShapeNet known categories | Chamfer distance: 8.74 -> 8.14 | Improved |
| add RFA aggregation (ablation) | NWoSFA · ShapeNet novel categories | Chamfer distance: 10.02 -> 10.08 | No clear effect |
| add GLFA aggregation (ablation) | NWoSFA · ShapeNet novel categories | Chamfer distance: 10.02 -> 9.98 | Improved |
| add refinement component (ablation) | NSFA-RFA · ShapeNet known categories | Chamfer distance: 8.65 -> 8.06 | Improved |
| add refinement component (ablation) | NSFA-GLFA · ShapeNet known categories | Chamfer distance: 9.38 -> 8.14 | Improved |
| add refinement component (ablation) | NSFA-RFA · ShapeNet novel categories | Chamfer distance: 10.09 -> 10.08 | No clear effect |
| add refinement component (ablation) | NSFA-GLFA · ShapeNet novel categories | Chamfer distance: 10.70 -> 9.98 | Improved |
| use RFA instead of GLFA aggregation | NSFA · ShapeNet known categories | Chamfer distance: 8.14 -> 8.06 | Improved |
| increase feature extraction levels from 5 to 6 (ablation) | NSFA-GLFA · ShapeNet known categories | Chamfer distance | Hurt |
| set known:missing mixture ratio to 1:3 or 0:4 instead of near 1:1 (ablation) | NSFA · ShapeNet known categories | Chamfer distance | Hurt |
| proposed vs PCN on dissimilar novel categories | NSFA-RFA · ShapeNet novel categories (dissimilar) | Chamfer distance: 12.90 -> 9.20 | Improved |
Closest papers by meaning
- Point Cloud Completion by Skip-Attention Network With Hierarchical Folding (CVPR 2020 · similarity 0.89)
- PointAttN: You Only Need Attention for Point Cloud Completion (AAAI 2024 · similarity 0.89)
- PointCFormer: A Relation-Based Progressive Feature Extraction Network for Point Cloud Completion (AAAI 2025 · similarity 0.88)
- FSC: Few-point Shape Completion (CVPR 2024 · similarity 0.88)
- Position-Aware Guided Point Cloud Completion with CLIP Model (AAAI 2025 · similarity 0.88)
- CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformers (AAAI 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.
