Self-supervised training of a depth estimation system

• Main Authors: MAC AODHA, OISIN, BROSTOW, GABRIEL J, FIRMAN, MICHAEL, GODARD, CLEMENT
• Format: Patent
• Language: Chinese; English
• Published: 16.01.2020
• Subjects: CALCULATING; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

A method for training a depth estimation model and methods for use thereof are described. Images are acquired and input into a depth model to extract a depth map for each of the plurality of images based on parameters of the depth model. The method includes inputting the images into a pose decoder to extract a pose for each image. The method includes generating a plurality of synthetic frames based on the depth map and the pose for each image. The method includes calculating a loss value with an input scale occlusion and motion aware loss function based on a comparison of the synthetic frames and the images. The method includes adjusting the plurality of parameters of the depth model based on the loss value. The trained model can receive an image of a scene and generate a depth map of the scene according to the image.