Learning depth from a single image, as an important issue in scene understanding, has attracted a lot of attention in the past decade.
The accuracy of the depth estimation has been improved by using deep learning neural networks. However, there exist inherent ambiguities in recovering 3D from a single 2D image.
In this project, We use deep learning based method for depth estimation.
experiments on the fixed- and varying-focal-length data sets demonstrate that the learned monocular depth with embedded focal length is significantly improved compared to that without embedding the focal length information.