Unsupervised Learning of Monocular Depth and Ego-Motion Using Multiple Masks
This work addresses depth and ego-motion estimation for robotics and autonomous driving, but it is incremental as it builds on existing unsupervised methods with mask-based improvements.
The paper tackles unsupervised learning of depth and ego-motion from monocular video by designing multiple masks to address occlusion and projection issues, achieving good performance on the KITTI dataset and demonstrating generalization to low-quality data.
A new unsupervised learning method of depth and ego-motion using multiple masks from monocular video is proposed in this paper. The depth estimation network and the ego-motion estimation network are trained according to the constraints of depth and ego-motion without truth values. The main contribution of our method is to carefully consider the occlusion of the pixels generated when the adjacent frames are projected to each other, and the blank problem generated in the projection target imaging plane. Two fine masks are designed to solve most of the image pixel mismatch caused by the movement of the camera. In addition, some relatively rare circumstances are considered, and repeated masking is proposed. To some extent, the method is to use a geometric relationship to filter the mismatched pixels for training, making unsupervised learning more efficient and accurate. The experiments on KITTI dataset show our method achieves good performance in terms of depth and ego-motion. The generalization capability of our method is demonstrated by training on the low-quality uncalibrated bike video dataset and evaluating on KITTI dataset, and the results are still good.