Simultaneous Localization And Mapping Constraints In Generative Adversarial Networks For Monocular Depth Estimation

摘要

The disclosure relates to systems, methods, and devices for determining a depth map of an environment based on a monocular image. A method for determining a depth map includes receiving a plurality of images from a monocular camera forming an image sequence. The method includes determining pose vector data for two successive images of the image sequence and providing the image sequence and the pose vector data to a generative adversarial network (GAN), wherein the GAN is trained using temporal constraints to generate a depth map for each image of the image sequence. The method includes generating a reconstructed image based on a depth map received from the GAN.