Publications | Datasets | CV

---

REDS_VTSR dataset

We provide the REalistic and Dynamic Scenes dataset for Video Temporal Super-Resolution (frame interpolation). Train and validation subsets are publicly available. Downloads are available via Google Drive and SNU CVLab server.

Google Drive

Type	Train	Validation	Test
15fps	train_15fps	val_15fps	test_15fps
30fps	train_30fps	val_30fps	test_30fps
60fps	train_60fps	val_60fps	test_60fps

SNU CVLab Server

Type	Train	Validation	Test
15fps	train_15fps	val_15fps	test_15fps
30fps	train_30fps	val_30fps	test_30fps
60fps	train_60fps	val_60fps	test_60fps

Updates

• We are planning to host an open-end public leaderboard site for the REDS related challenges. We will provide evaluated PSNR and SSIM for the submitted test results. Stay tuned for the updates!

Reference

The REDS_VTSR dataset was used in the AIM 2019 and AIM 2020 Challenges. If you find our dataset useful for your research, please consider citing our work:

• REDS_VTSR dataset and the AIM 2019 Challenge [paper] [arXiv] [slides]

@InProceedings{Nah_2019_ICCV_Workshops_REDS_VTSR,
  author = {Nah, Seungjun and Son, Sanghyun and Timofte, Radu and Lee, Kyoung Mu},
  title = {AIM 2019 Challenge on Video Temporal Super-Resolution: Methods and Results},
  booktitle = {ICCV Workshops},
  month = {Oct},
  year = {2019}
}

• REDS_VTSR AIM 2020 Challenge [paper] [arXiv] [slides]

@InProceedings{Son_2020_ECCV_Workshops_VTSR,
  author = {Son, Sanghyun and Lee, Jaerin and Nah, Seungjun and Timofte, Radu and Lee, Kyoung Mu},
  title = {AIM 2020 Challenge on Video Temporal Super-Resolution},
  booktitle = {ECCV Workshops},
  month = {Aug},
  year = {2020}
}

LICENSE

REDS_VTSR dataset is released under CC BY 4.0 license.