Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of GraphSearch.
Here we catalog, visually demonstrate, and discuss the main causes of commonly encountered visual distortions into current 360-degree video processing pipelines. The main goal of the samples in this dataset is to demonstrate the visual distortions discussed in the paper: Azevedo, Roberto G. de A.; Birbeck, N.; De Simone, F.; Janatra, I.; Adsumilli, B.; Frossard, P. (2019) Visual distortions in 360-degree videos. IEEE Transactions on Circuits and Systems for Video Technologies (TCSVT). https://infoscience.epfl.ch/record/262698 Since 360-degree videos are intended to be consumed on head-mounted displays (HMDs) the viewer will only have a full appreciation of the distortion by using them. We provide the full source content so that the viewers can also download and check the images/videos using a HMD.