Learning Depth from Monocular Videos Using Synthetic Data: A Temporally-Consistent Domain Adaptation Approach
arXiv:1907.06882
Abstract
Majority of state-of-the-art monocular depth estimation methods are supervised learning approaches. The success of such approaches heavily depends on the high-quality depth labels which are expensive to obtain. Some recent methods try to learn depth networks by leveraging unsupervised cues from monocular videos which are easier to acquire but less reliable. In this paper, we propose to resolve this dilemma by transferring knowledge from synthetic videos with easily obtainable ground-truth depth labels. Due to the stylish difference between synthetic and real images, we propose a temporally-consistent domain adaptation (TCDA) approach that simultaneously explores labels in the synthetic domain and temporal constraints in the videos to improve style transfer and depth prediction. Furthermore, we make use of the ground-truth optical flow and pose information in the synthetic data to learn moving mask and pose prediction networks. The learned moving masks can filter out moving regions that produces erroneous temporal constraints and the estimated poses provide better initializations for estimating temporal constraints. Experimental results demonstrate the effectiveness of our method and comparable performance against state-of-the-art.
References in corpus (8)
- Learning Transferable Features with Deep Adaptation Networks
- Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
- Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
- The ApolloScape Open Dataset for Autonomous Driving and its Application
- DepthTransfer: Depth Extraction from Video Using Non-parametric Sampling
- DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation
- Domain-Adversarial Neural Networks
- Learning Depth from Single Images with Deep Neural Network Embedding Focal Length