Research map / Point clouds / Shape and surface completion
Cascaded Refinement Network for Point Cloud Completion with Self-supervision
Xiaogang Wang, Marcelo H. Ang, Gimhee Lee
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 partial reconstruction auto-encoder and self-supervised strategies (SCRN vs CRN) | CRN · PCN dataset | mean Chamfer Distance: 8.505 -> 8.291 | Improved |
| add partial reconstruction and self-supervision (SCRN vs CRN) | CRN · ModelNet | mean Chamfer Distance: 2.606 -> 2.472 | Improved |
| add partial reconstruction and self-supervision (SCRN vs CRN) | CRN · Completion3D | mean Chamfer Distance: 9.21 -> 9.13 | Improved |
| train with CD-2 instead of CD-1 (ablation) | CRN · PCN dataset | mean Chamfer Distance: 8.868 -> 8.505 | Improved |
| add self-supervised strategies and unlabeled data with 10% labeled | PCN · ModelNet semi-supervised | Chamfer Distance: 6.520 -> 4.496 | Improved |
| add self-supervised strategies and unlabeled data with 10% labeled | CRN · ModelNet semi-supervised | Chamfer Distance: 4.291 -> 3.331 | Improved |
| add self-supervised strategies with 90% labeled | CRN · ModelNet semi-supervised | Chamfer Distance: 2.669 -> 2.433 | Improved |
| add mirroring operation (ablation) | CRN baseline · ModelNet bed | Chamfer Distance: 6.523 -> 6.331 | Improved |
| add contraction-expansion unit (ablation) | CRN baseline · ModelNet bed | Chamfer Distance: 6.523 -> 6.243 | Improved |
| add discriminator (ablation) | CRN baseline · ModelNet bed | Chamfer Distance: 6.523 -> 6.181 | Improved |
| add resampling strategy alone (ablation) | CRN · ModelNet 10% labeled | Chamfer Distance: 6.887 -> 4.838 | Improved |
| add MixUp alone (ablation) | CRN · ModelNet 10% labeled | Chamfer Distance: 6.887 -> 6.050 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- GRNet — GRNet: Gridding Residual Network for Dense Point Cloud Completion (ECCV 2020) · better on 3 of 4 shared results
- PMP-Net — PMP-Net: Point Cloud Completion by Learning Multi-Step Point Moving Paths (CVPR 2021) · better on 2 of 2 shared results
- SoftPoolNet — SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification (ECCV 2020) · 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
- Cascaded Refinement Network for Point Cloud Completion (CVPR 2020 · similarity 0.96)
- Complete Structure Guided Point Cloud Completion via Cluster- and Instance-Level Contrastive Learning (NeurIPS 2025 · similarity 0.92)
- P2C: Self-Supervised Point Cloud Completion from Single Partial Clouds (ICCV 2023 · similarity 0.92)
- DC-PCN: Point Cloud Completion Network with Dual-Codebook Guided Quantization (AAAI 2025 · similarity 0.91)
- PointAttN: You Only Need Attention for Point Cloud Completion (AAAI 2024 · similarity 0.89)
- CDPNet: Cross-Modal Dual Phases Network for Point Cloud Completion (AAAI 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.
