Multi-plane augmented reality image generation

The invention provides'multi-plane augmented reality image generation '. A set of training images is input into a neural network that outputs a pixel-by-pixel phase matrix that identifies pixels in the training images. Based on the pixel-by-pixel phase matrix, a spatial light modulator (SLM) is actuated to output an augmented reality (AR) image comprising a plurality of sub-images onto a vehicle windshield, each sub-image being output in one of a plurality of focal planes. Each training image corresponds to a respective sub-image. A feedback image of the AR image is obtained via an image sensor. An offset is determined based on comparing the training image to the feedback image. A parameter of a loss function is updated based on the offset, and the updated parameter is provided to the neural network to obtain an updated offset. 本公开提供了"多平面增强现实图像生成"。一组训练图像被输入到神经网络中，所述神经网络输出识别所述训练图像中的像素的逐像素相位矩阵。基于所述逐像素相位矩阵，空间光调制器(SLM)被致动以将包括多个子图像的增强现实(AR)图像输出到车辆挡风玻璃上，每个子图像在多个焦平面中的一者中输出。每个训练图像对应于一个相应子图像。所述AR图像的反馈图像经由图像传感器获得。偏移基于将