Prediction of depth from image data using statistical model

摘要

Systems and methods are described for predicting depth from color image data using a statistical model such as a convolutional neural network (CNN). The model is learned for binocular stereo image pairs and can predict depth data from a single source color image. For each image of the input binocular stereo pair, the model is trained to predict corresponding disparity values that, when applied to the image, enable reconstruction of other images. The model is updated based on a cost function that enhances consistency between predicted disparity values for each image of the stereo pair.