Moving Indoor: Unsupervised Video Depth Learning in Challenging Environments
arXiv:1910.08898
Abstract
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.
Accepted by ICCV2019
References in corpus (9)
- Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
- Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
- ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes
- DepthTransfer: Depth Extraction from Video Using Non-parametric Sampling
- Unsupervised Learning of Depth and Ego-Motion from Video
- Deep Ordinal Regression Network for Monocular Depth Estimation
- GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
- Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
- Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation