Monocular Image Depth Estimation Using a Conditional Generative Adversarial Net

Abstract

Depth estimation plays an essential part in understanding the three-dimensional (3D) geometric relations of a scene. Compared with other methods such as binocular vision, estimating depth from monocular image is much more challenging. In this paper, we propose a conditional generative adversarial net (cGAN) to tackle the problem of monocular image depth estimation. For enhancing the learning of our net in the training phrase, cycle consistency is applied to our network to form a closed loop. We use the network to model the mapping between the RGB images domain and the depth images domain. After training the network adequately, the model can output depth image according to the input RGB image. Experiments on NYU Depth v2 dataset demonstrate the proposed method outperforms state-of-art depth estimation approaches.