A simulation-based dataset featuring 20,000 stack configurations composed of a variety of elementary geometric primitives richly annotated regarding semantics and structural stability.
Source: ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking
Variants: ShapeStacks
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Unsupervised Object Segmentation | AST | Unsupervised Multi-object Segmentation Using Attention … | 2022-05-26 |
| Image Generation | GENESIS | GENESIS-V2: Inferring Unordered Object Representations … | 2021-04-20 |
| Image Generation | MONET-G | GENESIS-V2: Inferring Unordered Object Representations … | 2021-04-20 |
| Unsupervised Object Segmentation | GENESIS-V2 | GENESIS-V2: Inferring Unordered Object Representations … | 2021-04-20 |
| Unsupervised Object Segmentation | SlotAttention | GENESIS-V2: Inferring Unordered Object Representations … | 2021-04-20 |
| Unsupervised Object Segmentation | GENESIS | GENESIS-V2: Inferring Unordered Object Representations … | 2021-04-20 |
| Image Generation | GENESIS-V2 | GENESIS-V2: Inferring Unordered Object Representations … | 2021-04-20 |
| Unsupervised Object Segmentation | MONET-G | GENESIS-V2: Inferring Unordered Object Representations … | 2021-04-20 |
Recent papers with results on this dataset: