PartNet is a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information. The dataset consists of 573,585 part instances over 26,671 3D models covering 24 object categories. This dataset enables and serves as a catalyst for many tasks such as shape analysis, dynamic 3D scene modeling and simulation, affordance analysis, and others.
Source: PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding
Image Source: https://cs.stanford.edu/~kaichun/partnet/
Variants: PartNet
This dataset is used in 3 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| 3D Instance Segmentation | Semantic Segmentation-Assisted Instance Feature Fusion | Semantic Segmentation-Assisted Instance Feature Fusion … | 2022-08-09 |
| 3D Semantic Segmentation | FG-Net | FG-Net: Fast Large-Scale LiDAR Point … | 2020-12-17 |
| 3D Semantic Segmentation | MID-Net | Unsupervised 3D Learning for Shape … | 2020-08-03 |
| 3D Semantic Segmentation | closerlook3D | A Closer Look at Local … | 2020-07-02 |
| 3D Semantic Segmentation | CSN | Cross-Shape Attention for Part Segmentation … | 2020-03-20 |
| Instance Segmentation | PE | Point Cloud Instance Segmentation using … | 2019-11-30 |
| 3D Instance Segmentation | Probabilistic Embeddings | Point Cloud Instance Segmentation using … | 2019-11-30 |
| 3D Semantic Segmentation | DeepGCN | DeepGCNs: Making GCNs Go as … | 2019-10-15 |
| 3D Semantic Segmentation | PartNet | PartNet: A Large-scale Benchmark for … | 2018-12-06 |
| 3D Instance Segmentation | Partnet | PartNet: A Large-scale Benchmark for … | 2018-12-06 |
Recent papers with results on this dataset: