Context-based virtual object rendering

• Main Authors: MORENO DANIEL, SAMUEL EDWARD HARE, MAXIMOV LAZAROV MAKSIM, MATHEW TONY, MCPHEE ANDREW JAMES, SHANG WENTAO, GOODRICH KYLE
• Format: Patent
• Language: Chinese; English
• Published: 12.04.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

Aspects of the present disclosure relate to a system including a computer-readable storage medium storing at least one program and a method for rendering a virtual object in a real-world environment depicted in image content based on contextual information. A virtual object template is selected. One or more stylizations of the virtual object template are determined based on contextual information associated with the computing device. A virtual object is generated by applying one or more stylizations to a virtual object template. A virtual object is rendered within a 3D space captured within a camera feed of a computing device. 本公开内容的各方面涉及一种包括存储至少一个程序的计算机可读存储介质的系统以及用于基于上下文信息在图像内容中描绘的现实世界环境中渲染虚拟对象的方法。选择虚拟对象模板。基于与计算设备相关联的上下文信息确定虚拟对象模板的一个或更多个风格化。通过将一个或更多个风格化应用于虚拟对象模板来生成虚拟对象。在计算设备的摄像机馈送内捕获的3D空间内渲染虚拟对象。