EE S3eminar: Learn Stereo, Infer Mono: Siamese Networks for Unsupervised, Monocular, Depth Estimation
Speaker: Matan Goldman
M.Sc. student under the supervision of Prof. Tal Hassner and Prof. Shai Avidan
Wednesday, Oct 17th 2018 at 15:30
Room 206, Wolfson Mechanical Eng. Bldg., Faculty of Engineering
Learn Stereo, Infer Mono: Siamese Networks for Unsupervised, Monocular, Depth Estimation
Abstract
The field of unsupervised monocular depth estimation has seen huge advancements in recent years. Most methods assume stereo data is available during training but usually under-utilize it and only treat it as a reference signal. We propose a novel unsupervised approach which uses both left and right images equally during training, but can still be used with a single input image input at test time, for monocular depth estimation. Our Siamese network architecture consists of two, twin networks, each learns to predict a disparity map from a single image. At test time, however, only one of these networks is used in order to infer depth. We show state-of-the-art results on the standard KITTI Eigen split benchmark as well as being the highest scoring unsupervised method on the new KITTI single view benchmark. To demonstrate the ability of our method to generalize to new data sets, we further provide results on the Make3D benchmark, which was not used during training.
