Research map / Point clouds / Shape and surface completion
PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-Step Point Moving Paths
Xin Wen, Peng Xiang, Zhizhong Han, Yan-Pei Cao, Pengfei Wan, Wen Zheng, Yu-Shen Liu
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 PMD loss (ablation) | PMP-Net++ · PCN (avg) | Chamfer distance: 7.74 -> 7.56 | Improved |
| use RPA module instead of no path aggregation (ablation) | PMP-Net++ · Completion3D val (4 categories) | Chamfer distance: 8.09 -> 8.03 | Improved |
| use RPA instead of element-wise add (ablation) | PMP-Net++ · Completion3D val (4 categories) | Chamfer distance: 8.07 -> 8.03 | Improved |
| use RPA instead of GRU (ablation) | PMP-Net++ · Completion3D val (4 categories) | Chamfer distance: 8.27 -> 8.03 | Improved |
| use RPA instead of RNN (ablation) | PMP-Net++ · Completion3D val (4 categories) | Chamfer distance: 8.54 -> 8.03 | Improved |
| add transformer-enhanced encoder (PMP-Net to PMP-Net++) (ablation) | PMP-Net · Completion3D val (4 categories) | Chamfer distance: 11.58 -> 8.03 | Improved |
| increase deformation steps from 1 to 2 (ablation) | PMP-Net++ · Completion3D val (4 categories) | Chamfer distance: 9.45 -> 8.36 | Improved |
| increase deformation steps from 2 to 3 (ablation) | PMP-Net++ · Completion3D val (4 categories) | Chamfer distance: 8.36 -> 8.03 | Improved |
| increase deformation steps from 3 to 4 (ablation) | PMP-Net++ · Completion3D val (4 categories) | Chamfer distance: 8.03 -> 8.05 | No clear effect |
| use decreasing search radius [1.0,0.1,0.01] instead of constant [1.0,1.0,1.0] (ablation) | PMP-Net++ · Completion3D val (4 categories) | Chamfer distance: 8.69 -> 8.03 | Improved |
| use radius ratio 10 instead of [1.0,0.5,0.25] (ablation) | PMP-Net++ · Completion3D val (4 categories) | Chamfer distance: 8.54 -> 8.03 | Improved |
| add noise vector (dimension 32 vs 0) (ablation) | PMP-Net++ · Completion3D val (4 categories) | Chamfer distance: 11.10 -> 8.03 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 on most shared results.
- GRNet — GRNet: Gridding Residual Network for Dense Point Cloud Completion (ECCV 2020) · better on 4 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
- PU-GAN — PU-GAN: A Point Cloud Upsampling Adversarial Network (ICCV 2019) · 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
- FoldingNet — FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation (CVPR 2018) · 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
- PMP-Net: Point Cloud Completion by Learning Multi-Step Point Moving Paths (CVPR 2021 · similarity 0.98)
- Morphing and Sampling Network for Dense Point Cloud Completion (AAAI 2020 · similarity 0.90)
- FBNet: Feedback Network for Point Cloud Completion (ECCV 2022 · similarity 0.90)
- PCDreamer: Point Cloud Completion Through Multi-view Diffusion Priors (CVPR 2025 · similarity 0.89)
- DC-PCN: Point Cloud Completion Network with Dual-Codebook Guided Quantization (AAAI 2025 · similarity 0.89)
- SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance (AAAI 2025 · 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.
