Neurological light transmission

Examples relate to implementations of neural light transmission. A computing system may obtain data indicative of a plurality of UV texture maps and geometries of an object. Each UV texture map depicts an object from one of a plurality of views. The computing system may use the data to train a neural network to learn optical transfer functions. The light transfer function may be a continuous function that specifies how light interacts with the object when the object is viewed from the plurality of perspectives. The computing system may generate an output UV texture map depicting the object from a synthetic perspective based on the application of the light transfer function through the trained neural network. 示例涉及神经光传输的实现方式。计算系统可以获得指示对象的多个UV纹理图和几何形状的数据。每个UV纹理图从多个视角中的一个视角描绘对象。计算系统可以使用所述数据来训练神经网络以学习光传输函数。光传输函数可以是指定当从所述多个视角观察对象时光如何与对象相互作用的连续函数。计算系统可以基于通过经训练的神经网络对光传输函数的应用，生成从合成视角描绘对象的输出UV纹理图。