Video Super Resolution Datasets

DatasetYearTypeDownload LinkVideo NumberResolutionColor Space
V-train1Trainhttps://media.xiph.org/video/derf/25YUV
V-testTesthttps://media.xiph.org/video/derf/5YUV
Vid42011Testhttps://drive.google.com/drive/folders/10-gUO6zBeOpWE amrWKCtSkkUFukB9W5m4720 × 480RGB
YUV212014Testhttp://www.codersvoice.com/a/webbase/video/08/152014/ 130.html21352 × 288YUV
Venice2014Trainhttps://www.harmonicinc.com/free-4k-demo-footage/13, 840 × 2, 160RGB
Myanmar2014Trainhttps://www.harmonicinc.com/insights/blog/4k-in-context /13, 840 × 2, 160RGB
CDVL2016Trainhttp://www.cdvl.org/1, 920 × 1, 080RGB
Vimeo90K2019Train+Testhttp://toflow.csail.mit.edu/91,701448 × 256RGB
REDS2019Train+Testhttps://seungjunnah.github.io/Datasets/reds.html2701, 920 × 1, 080RGB
UVG2020Testhttp://ultravideo.cs.tut.fi/163, 840 × 2, 160YUV

Vid4

Videoset4 consists of the four test videos: walk, foliage, city, and calendar.

Vimeo90k

This dataset consists of 89,800 video clips downloaded from vimeo.com, which covers large variaty of scenes and actions. It is designed for the following four video processing tasks: temporal frame interpolation, video denoising, video deblocking, and video super-resolution.

UVG

The open Ultra Video Group (UVG) dataset is composed of 16 versatile 4K (3840×2160) test video sequences captured at 50/120 fps.

Challenges

NameYearOrganizerLocationWebsiteDatasetScaleChampionPSNRSSIM
NTIRE 2019 Video Restoration and Enhancement Challenges2019CVPRLong Beach, Californiahttps://data.vision.ee.e thz.ch/cvl/ntire19/REDS×4EDVR [24]31.790.8962
YOUKU Video Super-Resolution and Enhancement Challenge2019AlibabaHangzhou, Chinahttps://tianchi.aliyun.c om/competition/entra nce/231711/introductio nYouku-VESR×4VESR-Net [84]37.85
AIM 2019 Challenge on Video Extreme Super-Resolution2019ECCVHong Kong, Chinahttps://www.aim2019. org/Vid3oC×16EDVR+22.530.64
Mobile Restoration ChallengeVideo2019ICIP & Kwaihttps://www.kuaishou .com/activity/icip2019
AIM 2020 Challenge on Video Extreme Super-Resolution2020ECCVBoston, Massachusettshttp://aim2020.org/×16

Leave a Reply Cancel reply