Update README.md

README.md

@@ -1,10 +1,123 @@
 ---
-title: README
-emoji: 📊
-colorFrom: yellow
-colorTo: blue
-sdk: static
-pinned: false
+pretty_name: CARD – Cariad Road Dataset
+task_categories:
+- depth-estimation
+- object-detection
+- image-to-3d
+tags:
+- autonomous-driving
+- depth
+- stereo
+- lidar
+- computer-vision
+- benchmark
+size_categories:
+- 1M<n<10M
+title: Cariad Road Dataset
+emoji: 🐢
+short_description: Collection of all the published datasets
 ---
 
-This data is to be officially published soon. 
+
+# CARD – Cariad Road Dataset
+
+> **This page is the central index for all CARD dataset releases.**  
+> Each sub-dataset has its own repository linked below.
+
+---
+
+## What is CARD?
+
+CARD is a multi-modal driving dataset designed for research in
+**depth estimation**, **3D reconstruction**, **object detection**, and related
+autonomous-driving tasks. Data was recorded across Germany & Italy and
+conditions using a calibrated stereo camera rig paired with 2x LiDAR
+and IMU, yielding rich synchronized multi-modal recordings.
+
+Key properties:
+- 🎥 **Stereo camera** images (cam_0 / cam_1) at full resolution
+- 📡 **LiDAR** point clouds + IMU signals
+- 🏷️ **YOLO-format** bounding-box annotations
+- 📐 **Aggregated depth** point clouds (`agg_depth/`) for dense ground-truth depth, which are quasi-dense 3D ground-truth, processed by aggregation of the lidar, while removing dynamic objects artifacts
+- 🕐 **Temporal consistency** – all modalities share synchronized timestamps
+- 🔒 **Privacy-preserved** – faces and license plates anonymized
+
+---
+
+## Dataset Index
+
+| Repository | Region | # Sequences | License | Notes |
+|---|---|---|---|---|
+| [CARD-Germany-Batch1](https://huggingface.co/datasets/CARD-DATA/CARD-Germany-Batch1) | Germany (2 days) | 28 | CC BY 4.0 | Includes night sequences (`night` in name = after 17:30) |
+| [CARD-Germany-Batch2](https://huggingface.co/datasets/CARD-DATA/CARD-Germany-Batch2) | Germany (Stuttgart area) | 22 | CC BY 4.0 | |
+| [CARD-Germany-Batch3](https://huggingface.co/datasets/CARD-DATA/CARD-Germany-Batch3) | Germany (Munich → Ingolstadt) | 30 | CC BY 4.0 | Long-route highway + urban |
+| [CARD-Italy](https://huggingface.co/datasets/CARD-DATA/CARD-Italy) | Italy | 38 | CC BY-NC 4.0 | Non-commercial only |
+
+> **Note:** Sequences prefixed with `unused_` in any sub-dataset are not part of
+> any official train / val / test split and are provided for completeness only.
+
+---
+
+## Data Format
+
+Every sequence across all sub-datasets follows the same folder structure:
+
+```
+<dataset>/<sequence>/
+├── img/
+│   ├── cam_0/          # Left camera images
+│   └── cam_1/          # Right camera images
+├── raw/                # LiDAR point clouds + IMU signals
+├── labels/             # YOLO-format bounding-box annotations
+├── export/             # Trajectory, calibration, and metadata
+└── agg_depth/          # Aggregated depth point clouds (dense GT depth)
+```
+
+---
+
+## Splits
+
+Official **train / val / test** splits are provided as part of the
+[CARD-SDK](https://github.com/CARD-Data/CARD-sdk) development kit.
+
+---
+
+## License and Usage Terms
+
+| Sub-dataset | License |
+|---|---|
+| CARD-Germany-Batch1 | [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) |
+| CARD-Germany-Batch2 | [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) |
+| CARD-Germany-Batch3 | [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) |
+| CARD-Italy | [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) – **non-commercial only** |
+
+We have taken reasonable measures to remove personally identifiable information
+(e.g., faces and license plates). To request removal of specific images from the
+dataset, please contact **gasser.elazab@cariad.technology**.
+
+The purpose of the CARD project is to help improve road safety and make driving
+safer. We encourage use of this dataset toward that goal, and it is forbidden to
+use it for any military use.
+
+---
+
+## Development Kit
+
+A development kit (CARD-SDK) with tools to load, visualize, and evaluate on the
+CARD datasets is going to be released soon.
+
+---
+
+## Citation
+
+If you use any CARD sub-dataset in your work, please cite the corresponding entry:
+
+```bibtex
+@inproceedings{elazab2025card,
+  title={CARD: A Multi-Modal Automotive Dataset for Dense 3D Reconstruction in Challenging Road Topography},
+  author={Elazab, Gasser and Neuhaus, Frank and Ko{ss}, Tilman and Splietker, Malte and Date, Aditya and Unterreiner, Michael and Jansen, Maximilian and Hellwich, Olaf},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+  year={2026}
+}
+}
+```