Update README.md

Author: tzole1155

README.md

@@ -8,17 +8,27 @@
 ## TODO
 - [x] Add DJI M2ED drone model.
 - [x] Add colour, depth, and silhouettes from an exocentic view.
-- [x] Add colour, and depth, an egocentric view.
-- [ ] Add UAVA toolset.
-- [ ] Add data loaders.
+- [x] Add colour, and depth, from an egocentric view.
+- [x] Add UAVA toolset.
+- [x] Add data loaders.
 - [ ] Add normals, and optical flow from an exocentic view.
 - [ ] Add normals, and optical flow from an egocentic view.
 - [ ] Add new drone models.
 
 
-## **UAVA toolset**
+# UAVA Toolset
+A set of tools for working with the [UAVA dataset] (https://vcl3d.github.io/UAVA/)
+  - Pytorch data loaders
+  - Dataset splits generation scripts
+  - Visualisation script
 
-TODO: A set of tools for facilitating the usage of the UAVA dataset.
+The **UAVA** dataset was generated following a carefully data synthesis pipeline for ensuring the generation of photorealistic images and realistic trajectories.
+ 
 
-## Data Loaders
-TODO: Add dataloaders
+## Data Loading
+An example data loading usage can be found in ['visualize_dataset.py'](./visualize_dataset.py) where the dataset is loaded and visualized using visdom.
+
+Given that **UAVA** dataset can be used in a variatety of tasks ranging from computer vision to robotics, data loading can be modified accordingly w.r.t. `drone model` , `camera views`, `image types` and `time frames`.
+
+## Splits
+The data splits follow the same distribution of the [Matterport3D](https://niessner.github.io/Matterport/) dataset and can be found in the [data splits](data splits) folder.