Awesome

ESIM_dataset

Event camera dataset made by Lin Wang @Visual Intelligence Lab. of KAIST. Our datasets inlcudes various scenes for image/video reconstruction, restoration and super-resolution. The link below includes both datasets for two papers 'Event-based High Dynamic Range Image and Very High Frame Rate Video Generation using Conditional Generative Adversarial Networks' and 'EventSR: From Asynchronous Events to Image Reconstruction, Restoration, and Super-Resolution via End-to-End Adversarial Learning'. For CVPR2019, the dataset is for training supervised image/video reconstruction from events via adversarial learning. The dataset includes various sences (e.g., buildings, grass, trees, tables, rooms etc.,) which are characterised by distinctive corners, edges, etc. For CVPR2020, the dataset is mainly targeted for image restoration and super-resolution. The dataset consists of three parts: ESIM-SR data (made using the mainstream RGB SISR images [41,48]), SIM-RW data (made using the reference color images from event camera dataset [28] in the main paper) and RW-SR data ( made by changing the RGB images to grayscale images [41,48])

Since the dataset is hugh in size, we could not provide them here, instead we put them in Baidu drive which is convenient to download.

The dataset link is: https://pan.baidu.com/s/14IEOUrMRtX5G79Z3NdkZLg password: tg32

If you use any of the dataset, please cite the following publications:

@inproceedings{wang2019event, title={Event-based high dynamic range image and very high frame rate video generation using conditional generative adversarial networks}, author={L. {Wang} and I. S. M. {Mostafavi} and Y. {Ho} and K. {Yoon}}, booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, pages={10081--10090}, year={2019} }

@inproceedings{wang2020eventsr, title={EventSR: From Asynchronous Events to Image Reconstruction, Restoration, and Super-Resolution via End-to-End Adversarial Learning}, author={Wang, Lin and Kim, Tae-Kyun and Yoon, Kuk-Jin}, booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, year={2020} }

If you have any questions, please feel free to email us:wanglin@kaist.ac.kr.