The Vid3oC and IntVID datasets for video super resolution and quality mapping

• Main Authors: KIM, S., LI, G., FUOLI, D., DANELLJAN, M., HUANG, Zhiwu, GU, S., TIMOFTE, R.
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2019
• Subjects: Dataset; Video quality mapping; Video super resolution; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/6547; https://ink.library.smu.edu.sg/context/sis_research/article/7550/viewcontent/The_Vid3oC_and_IntVID_Datasets_for.pdf
• Institution: Singapore Management University

The current rapid advancements of computational hardware has opened the door for deep networks to be applied for real-time video processing, even on consumer devices. Appealing tasks include video super-resolution, compression artifact removal, and quality enhancement. These problems require high-quality datasets that can be applied for training and benchmarking. In this work, we therefore introduce two video datasets, aimed for a variety of tasks. First, we propose the Vid3oC dataset, containing 82 simultaneous recordings of 3 camera sensors. It is recorded with a multi-camera rig, including a high-quality DSLR camera, a high-end smartphone, and a stereo camera sensor. Second, we introduce the IntVID dataset, containing over 150 high-quality videos crawled from the internet. The datasets were employed for the AIM 2019 challenges for video super-resolution and quality mapping.