Moving Indoor: Unsupervised Video Depth Learning in Challenging Environments
This addresses the problem of depth estimation in indoor scenes for computer vision applications, representing an incremental advance by adapting existing unsupervised methods to a new domain.
The paper tackles the challenge of applying unsupervised video depth learning to indoor environments with non-texture regions and complex camera motion, achieving results comparable to fully supervised methods on the NYU Depth V2 benchmark.
Recently unsupervised learning of depth from videos has made remarkable progress and the results are comparable to fully supervised methods in outdoor scenes like KITTI. However, there still exist great challenges when directly applying this technology in indoor environments, e.g., large areas of non-texture regions like white wall, more complex ego-motion of handheld camera, transparent glasses and shiny objects. To overcome these problems, we propose a new optical-flow based training paradigm which reduces the difficulty of unsupervised learning by providing a clearer training target and handles the non-texture regions. Our experimental evaluation demonstrates that the result of our method is comparable to fully supervised methods on the NYU Depth V2 benchmark. To the best of our knowledge, this is the first quantitative result of purely unsupervised learning method reported on indoor datasets.