Efficient Bayesian deep inversion

Abstract

We develop a deep learning method to enhance sensor detection for depth prediction. Our novel system combines sensor hardware and Bayesian inference to solve the underlying inverse problem, recovering depth from measurements. The hardware comprises single sensor non-scanning time-of-flight laser detection with synchronised video to produce a 3D depth map. The Bayesian framework provides depth prediction with uncertainty quantification. A conditional generator-discriminator adversarial network is adapted to learn a compact representation of the scene that recovers 3D depth at 30 Hz using a large training set. We transfer the network to a real hardware system and compare with ground truth depth information. Our novel synthesis of hardware and machine learning technologies addresses the important challenge of providing accurate absolute depth prediction at video rate with efficient and cost-effective non-scanning laser detection technology. This flexible and compact system has many exciting applications for autonomous vehicles, drones and wearable technology.