Research map / Point clouds / Point cloud classification
Progressive Seed Generation Auto-Encoder for Unsupervised Point Cloud Learning
Juyoung Yang, Pyunghwan Ahn, Doyeon Kim, Haeil Lee, Junmo Kim
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 |
|---|---|---|---|
| replace random uniform seed with fixed grid seed (ablation) | FoldingNet-style decoder · ShapeNetCorev2 (decoder ablation, PointNet encoder) | chamfer distance x10^4: 7.96 -> 7.43 | Improved |
| generate 2D seed from codeword instead of random seed (ablation) | FoldingNet-style decoder · ShapeNetCorev2 (decoder ablation, PointNet encoder) | chamfer distance x10^4: 7.96 -> 7.34 | Improved |
| generate 2D seed from codeword instead of fixed grid (ablation) | FoldingNet-style decoder · ShapeNetCorev2 (decoder ablation, PointNet encoder) | chamfer distance x10^4: 7.43 -> 7.34 | Improved |
| expand generated seed from 2D points to 32-dimensional features (ablation) | Decoder C2 · ShapeNetCorev2 (decoder ablation, PointNet encoder) | chamfer distance x10^4: 7.34 -> 6.84 | Improved |
| add seed feature propagation modules (1 to 3) progressively (ablation) | Decoder C32 · ShapeNetCorev2 (decoder ablation, PointNet encoder) | chamfer distance x10^4: 6.84 -> 6.38 | Improved |
| add a third SFPM after two (ablation) | Decoder C32 + 2 SFPMs · ShapeNetCorev2 (decoder ablation, PointNet encoder) | chamfer distance x10^4: 6.40 -> 6.38 | No clear effect |
| use 1024-dim codeword instead of 512-dim (ablation) | PSG-Net · ShapeNetCorev2 reconstruction | chamfer distance x10^4: 5.78 -> 5.15 | Improved |
| add seed generation module to AtlasNet with 32 patches | AtlasNet · ShapeNetCorev2 reconstruction | chamfer distance x10^4: 5.66 -> 5.31 | Improved |
| combine PSG-Net decoder with PointGLR | PointGLR · ModelNet40 unsupervised classification | accuracy (%): 92.22 -> 92.59 | Improved |
| use single-patch PSG-Net instead of multi-patch AtlasNet | AtlasNet-125 · ShapeNetCorev2 reconstruction | chamfer distance x10^4: 5.66 -> 5.78 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 4 on most shared results.
- FoldingNet — FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation (CVPR 2018) · 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
- SoftPoolNet — SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification (ECCV 2020) · better on 0 of 1 shared result
- GRNet — GRNet: Gridding Residual Network for Dense Point Cloud Completion (ECCV 2020) · 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
- Learning Progressive Point Embeddings for 3D Point Cloud Generation (CVPR 2021 · similarity 0.88)
- DiffPMAE: Diffusion Masked Autoencoders for Point Cloud Reconstruction (ECCV 2024 · similarity 0.87)
- Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification (CVPR 2021 · similarity 0.87)
- LPCG: A Self-conditional Architecture for Labeled Point Cloud Generation (AAAI 2025 · similarity 0.87)
- 3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining (ICLR 2024 · similarity 0.87)
- Orthogonal Dictionary Guided Shape Completion Network for Point Cloud (AAAI 2024 · similarity 0.85)
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.
