Research map / Point clouds / Point cloud classification
SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification
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 L_inter (ablation) | SoftPoolNet · ShapeNet completion 2048 points | Chamfer distance x10^3: 15.97 -> 8.31 | Improved |
| add L_intra (ablation) | SoftPoolNet · ShapeNet completion 2048 points | Chamfer distance x10^3: 11.67 -> 8.31 | Improved |
| add L_boundary (ablation) | SoftPoolNet · ShapeNet completion 2048 points | Chamfer distance x10^3: 9.03 -> 8.31 | Improved |
| add L_preserve (ablation) | SoftPoolNet · ShapeNet completion 2048 points | Chamfer distance x10^3: 15.37 -> 8.31 | Improved |
| add L_inter (ablation) | SoftPoolNet · ModelNet40 (unsupervised features + SVM) | accuracy: 89.40% -> 92.28% | Improved |
| add L_intra (ablation) | SoftPoolNet · ModelNet40 (unsupervised features + SVM) | accuracy: 83.70% -> 92.28% | Improved |
| add L_boundary (ablation) | SoftPoolNet · ModelNet40 (unsupervised features + SVM) | accuracy: 88.26% -> 92.28% | Improved |
| add L_preserve (ablation) | SoftPoolNet · ModelNet40 (unsupervised features + SVM) | accuracy: 86.09% -> 92.28% | Improved |
| add L_boundary | FoldingNet · ShapeNet completion 16384 points | Chamfer distance x10^3: 10.07 -> 9.65 | Improved |
| add L_boundary | PCN · ShapeNet completion 16384 points | Chamfer distance x10^3: 9.64 -> 8.26 | Improved |
| add L_boundary | AtlasNet · ShapeNet completion 2048 points | Chamfer distance x10^3: 17.69 -> 16.56 | Improved |
| vary (N_f, N_r) from (2, 128) to (8, 32) (ablation) | SoftPoolNet · ShapeNet completion 16384 points | Chamfer distance x10^3: 7.80 -> 5.94 | Improved |
Later papers that compared with this method
6 later accepted papers report SoftPoolNet as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- SoftPool++: An Encoder–Decoder Network for Point Cloud Completion (IJCV 2022 · better on 3 of 3 shared results)
- PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-Step Point Moving Paths (TPAMI 2022 · better on 1 of 1 shared result)
- ME-PCN: Point Completion Conditioned on Mask Emptiness (ICCV 2021 · better on 2 of 2 shared results)
- SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution With Skip-Transformer (ICCV 2021 · better on 1 of 1 shared result)
- Progressive Seed Generation Auto-Encoder for Unsupervised Point Cloud Learning (ICCV 2021 · better on 0 of 1 shared result)
- Cascaded Refinement Network for Point Cloud Completion with Self-supervision (TPAMI 2021 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FoldingNet — FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation (CVPR 2018) · better on 2 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
- SoftPool++: An Encoder–Decoder Network for Point Cloud Completion (IJCV 2022 · similarity 0.95)
- PointAttN: You Only Need Attention for Point Cloud Completion (AAAI 2024 · similarity 0.90)
- DC-PCN: Point Cloud Completion Network with Dual-Codebook Guided Quantization (AAAI 2025 · similarity 0.90)
- GRNet: Gridding Residual Network for Dense Point Cloud Completion (ECCV 2020 · similarity 0.90)
- DeCoTR: Enhancing Depth Completion with 2D and 3D Attentions (CVPR 2024 · similarity 0.87)
- PointCFormer: A Relation-Based Progressive Feature Extraction Network for Point Cloud Completion (AAAI 2025 · similarity 0.87)
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.
