Self-Supervised Deep Visual Odometry with Online Adaptation
arXiv:2005.06136
Abstract
Self-supervised VO methods have shown great success in jointly estimating camera pose and depth from videos. However, like most data-driven methods, existing VO networks suffer from a notable decrease in performance when confronted with scenes different from the training data, which makes them unsuitable for practical applications. In this paper, we propose an online meta-learning algorithm to enable VO networks to continuously adapt to new environments in a self-supervised manner. The proposed method utilizes convolutional long short-term memory (convLSTM) to aggregate rich spatial-temporal information in the past. The network is able to memorize and learn from its past experience for better estimation and fast adaptation to the current frame. When running VO in the open world, in order to deal with the changing environment, we propose an online feature alignment method by aligning feature distributions at different time. Our VO network is able to seamlessly adapt to different environments. Extensive experiments on unseen outdoor scenes, virtual to real world and outdoor to indoor environments demonstrate that our method consistently outperforms state-of-the-art self-supervised VO baselines considerably.
Accepted by CVPR 2020 oral
References in corpus (10)
- Overcoming catastrophic forgetting in neural networks
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks
- A Simple Neural Attentive Meta-Learner
- On the Number of Linear Regions of Deep Neural Networks
- GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
- Streaming Variational Bayes
- Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction
- Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry
- Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry