s3dis datasets need preprocessing?

### Checklist

- [x] I have searched for [similar issues](https://github.com/isl-org/Open3D-ML/issues).
- [x] I have tested with the [latest development wheel](http://www.open3d.org/docs/latest/getting_started.html#development-version-pip).
- [x] I have checked the [release documentation](http://www.open3d.org/docs/release/) and the [latest documentation](http://www.open3d.org/docs/latest/) (for `main` branch).

### My Question

I am trying to reproduce the training on the S3DIS dataset.
The dataset dir is
```
datasets/
└── S3DIS
└── Stanford3dDataset_v1.2_Aligned_Version
├── Area_1
│   ├── pantry_1
│   │   └── Annotations
│   └── WC_1
│   └── Annotations
├── Area_2
│   ├── pantry_1
│   │   └── Annotations
│   └── WC_1
│   └── Annotations
├── Area_3
│   ├── pantry_1
│   │   └── Annotations
│   └── WC_1
│   └── Annotations
├── Area_4
│   ├── pantry_1
│   │   └── Annotations
│   └── WC_1
│   └── Annotations
├── Area_5
│   ├── pantry_1
│   │   └── Annotations
│   └── WC_1
│   └── Annotations
├── Area_6
│   ├── pantry_1
│   │   └── Annotations
│   └── WC_1
│   └── Annotations
└── original_pkl

```
Do I need to manually perform data preprocessing operations?