Access the Challenge Dataset
Training Data:
[Baidu Netdisk]
[OneDrive]
Validation Data(input):
[Baidu Netdisk]
[OneDrive]
Testing Data(input):
[TBD]
[TBD]
The Dataset is for this chanllenge and research purpose only. Commercial use is not permitted.
Content of The Downloaded Package
In the dataset, you may find a folder for training data and a folder for testing data.
Data format
Both the training and testing data are stored in hdf5 format, you can use h5py tool to read the data. To create a pytorch dataset, please refer to(https://github.com/TimoStoff/event_cnn_minimal/blob/master/data_loader/dataset.py)
The structure tree of the Event-to-HDR dataset is shown below
Train
The training dataset consists of 20 HDR videos paired with their corresponding event streams. Each video spans 2.8 seconds, captured at 500fps, resulting in a total of 2828 frames per video. The resolution of both the event streams and videos is 320x240.
Validation
The validation set includes 6 event streams, Unlike the Training sets, validation set only include event streams, without HDR ground truth.
Test
In the test set, participants will find 6 event streams. Like the validation sets, the test set does not include the HDR videos, with only event stream data as input.
Citation
If you use this dataset for any purpose, please cite our previous work