LDV stands for Large-scale Diverse Video, which is a video enhancement dataset. The dataset contains 240 high-quality videos with a resolution of 960×536 pixels. LDV has good diversity in video content, inter-frame motion, shooting method, light brightness, and frame rate.

Citation

@inproceedings{yang2021dataset, title={{NTIRE 2021} Challenge on Quality Enhancement of Compressed Video: Dataset and Study}, author={Ren Yang and Radu Timofte}, booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops}, year={2021} } @inproceedings{yang2021ntire, title={{NTIRE 2021} Challenge on Quality Enhancement of Compressed Video: Methods and Results}, author={Ren Yang and Radu Timofte and others}, booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops}, year={2021} }