NEURAL NETWORK BASED PATCH BLENDING FOR IMMERSIVE VIDEO

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 ge...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	BOYCE JILL, RAZIEL BEN, ASHKENAZI TZACH, KATS EYTAN, BAUMAN GILAD, SHILONI ASAF, BEER ILAN
Format:	Patent
Sprache:	chi ; eng
Schlagworte:	ELECTRIC COMMUNICATION TECHNIQUE ELECTRICITY PICTORIAL COMMUNICATION, e.g. TELEVISION
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	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. 实施例总体上涉及一种用于沉浸式视频的基于神经网络的补片混合。系统的实施例包括一个或多个处理器核；用于存储沉浸式视频中的图像的数据的存储器；以及神经网络训练框架。所述神经网络训练框架用于生成经训练的神经网络，所述经训练的神经网络用于将对象的视图与针对所述对象的一个或多个检测到的遮挡生成的补片混合。