Research map / Point clouds / Point cloud classification
Unsupervised Point Cloud Representation Learning With Deep Neural Networks: A Survey
Aoran Xiao, Jiaxing Huang, Dayan Guan, Xiaoqin Zhang, Shijian Lu, Ling Shao
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 unsupervised Point-BERT pre-training | Transformer · ScanObjectNN OBJ-BG | accuracy: 79.9 -> 87.4 | Improved |
| add unsupervised Point-BERT pre-training | Transformer · ModelNet40 | accuracy: 91.2 -> 93.4 | Improved |
| add unsupervised OcCo pre-training | PointNet · ScanObjectNN OBJ-BG | accuracy: 73.5 -> 80.0 | Improved |
| add unsupervised OcCo pre-training | DGCNN · ModelNet40 | accuracy: 92.5 -> 93.0 | Improved |
| add unsupervised Info3D pre-training | DGCNN · ModelNet40 | accuracy: 93.5 -> 93.0 | Hurt |
| add Jigsaw3D pre-training | PCN · ScanObjectNN OBJ-BG | accuracy: 78.3 -> 78.2 | No clear effect |
| add unsupervised Point-BERT pre-training | Transformer · ShapeNetPart | class mIoU: 83.4 -> 84.1 | Improved |
| add OcCo pre-training | Transformer · ShapeNetPart | class mIoU: 83.4 -> 83.4 | No clear effect |
| add ParAE pre-training | DGCNN · S3DIS Area 5 (train Area1) | mIoU: 43.6 -> 53.5 | Improved |
| add Jigsaw3D pre-training | DGCNN · S3DIS Area 5 (train Area1) | mIoU: 43.6 -> 44.7 | Improved |
Closest papers by meaning
- Deep Learning for 3D Point Clouds: A Survey (TPAMI 2020 · similarity 0.90)
- Self-Supervised Deep Learning on Point Clouds by Reconstructing Space (NeurIPS 2019 · similarity 0.89)
- A Survey of Label-Efficient Deep Learning for 3D Point Clouds (TPAMI 2024 · similarity 0.89)
- Unsupervised Point Cloud Representation Learning by Clustering and Neural Rendering (IJCV 2024 · similarity 0.89)
- Unsupervised Point Cloud Pre-Training via Occlusion Completion (ICCV 2021 · similarity 0.89)
- DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis (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.
