Author(s)

Barnabas Takacs¹, Zsuzsanna Vincze¹, Hannes Fassold², Antonis Karakottas³, Nikolaos Zioulis³, Dimitrios Zarpalas³, Petros Daras³

¹Drukka Kft/PanoCAST, Budapest, Hungary.
²Joanneum Research Digital—Institute for Information and Communication Technologies, Graz, Austria.
³Centre for Research & Technology Hellas (CERTH)—Information Technologies Institute (ITI), Thessaloniki, Greece.

We describe four fundamental challenges that complex real-life Virtual Reality (VR) productions are facing today (such as multi-camera management, quality control, automatic annotation with cinematography and 360˚ depth estimation) and describe an integrated solution, called Hyper 360, to address them. We demonstrate our solution and its evaluation in the context of practical productions and present related results.

Deep Learning, Tensor Flow, YoloV3, 360˚ Video, Virtual Reality, Free Viewpoint Video, Quality Control, Automatic Cinematography, Multi-Camera Systems

Takacs, B. , Vincze, Z. , Fassold, H. , Karakottas, A. , Zioulis, N. , Zarpalas, D. and Daras, P. (2019) Hyper 360—Towards a Unified Tool Set Supporting Next Generation VR Film and TV Productions. Journal of Software Engineering and Applications, 12, 127-148. doi: 10.4236/jsea.2019.125009.