Neural network based patch blending for immersive video
US10819968B2 · kind B2 · utility
13Cited by
3References
16Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jul 31, 2018 |
| Grant date | Oct 27, 2020 |
| Priority date | — |
| Expiry date | Jul 31, 2038 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04N13/344
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
Embodiments are generally directed to neural network based patch blending for immersive video. An embodiment of a system includes one or more processor cores; a memory to store data for images in immersive video; and a neural network training framework. The neural network training framework is to generate a trained neural network for blending of a view of an object with patches generated for one or more detected occlusions for the object.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.