The ObjectsRoom dataset is based on the MuJoCo environment used by the Generative Query Network [4] and is a multi-object extension of the 3d-shapes dataset. The training set contains 1M scenes with up to three objects. We also provide ~1K test examples for the following variants:
2.1 Empty room: scenes consist of the sky, walls, and floor only.
2.2 Six objects: exactly 6 objects are visible in each image.
2.3 Identical color: 4-6 objects are placed in the room and have an identical, randomly sampled color.
Datapoints consist of an image and fixed number of masks. The first four masks correspond to the sky, floor, and two halves of the wall respectively. The remaining masks correspond to the foreground objects.
Source: Objects Room
Variants: ObjectsRoom
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: