Research map / Point clouds / Shape and surface completion
SoftPool++: An Encoder–Decoder Network for Point Cloud Completion
Yida Wang, David Joseph Tan, Nassir Navab, Federico Tombari
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 skip-connection with feature transform (ablation) | SoftPool++ · Completion3D 2048 pts (L2 Chamfer x1e4) | Chamfer distance: 10.63 -> 9.36 | Improved |
| add regularization LR on feature transform (ablation) | SoftPool++ · Completion3D 2048 pts (L2 Chamfer x1e4) | Chamfer distance: 11.35 -> 9.36 | Improved |
| add discriminative training D (ablation) | SoftPool++ · Completion3D 2048 pts (L2 Chamfer x1e4) | Chamfer distance: 9.59 -> 9.36 | Improved |
| add Linter loss (ablation) | SoftPool++ · Completion3D 2048 pts (L1 Chamfer x1e4) | Chamfer distance: 14.67 -> 7.48 | Improved |
| add Lintra loss (ablation) | SoftPool++ · Completion3D 2048 pts (L1 Chamfer x1e4) | Chamfer distance: 10.62 -> 7.48 | Improved |
| add Lpreserve loss (ablation) | SoftPool++ · Completion3D 2048 pts (L1 Chamfer x1e4) | Chamfer distance: 13.68 -> 7.48 | Improved |
| add Lboundary loss (ablation) | SoftPool++ · Completion3D 2048 pts (L1 Chamfer x1e4) | Chamfer distance: 8.65 -> 7.48 | Improved |
| add Lboundary to PCN | PCN · Completion3D 2048 pts (L1 Chamfer x1e4) | Chamfer distance: 14.72 -> 13.49 | Improved |
| add Lboundary to AtlasNet | AtlasNet · Completion3D 2048 pts (L1 Chamfer x1e4) | Chamfer distance: 17.69 -> 16.56 | Improved |
| add skip-connection (ablation) | SoftPool++ · ModelNet40 classification | accuracy: 93.17 -> 94.75 | Improved |
| add Lintra loss (ablation) | SoftPool++ · ModelNet40 classification | accuracy: 84.98 -> 94.75 | Improved |
| replace PointNet feature by SoftPool++ feature | FoldingNet · PCN dataset 16384 pts (L2 Chamfer x1e3) | Chamfer distance: 7.14 -> 7.00 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 on most shared results.
- FoldingNet — FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation (CVPR 2018) · better on 4 of 4 shared results
- SoftPoolNet — SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification (ECCV 2020) · better on 3 of 3 shared results
- GRNet — GRNet: Gridding Residual Network for Dense Point Cloud Completion (ECCV 2020) · better on 2 of 2 shared results
- PMP-Net — PMP-Net: Point Cloud Completion by Learning Multi-Step Point Moving Paths (CVPR 2021) · better on 0 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
- SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification (ECCV 2020 · similarity 0.95)
- 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 0.90)
- DeCoTR: Enhancing Depth Completion with 2D and 3D Attentions (CVPR 2024 · similarity 0.89)
- PointCFormer: A Relation-Based Progressive Feature Extraction Network for Point Cloud Completion (AAAI 2025 · similarity 0.89)
- PCDreamer: Point Cloud Completion Through Multi-view Diffusion Priors (CVPR 2025 · 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.
