SAda-Net: A Self-Supervised Adaptive Stereo Estimation CNN For Remote Sensing Image Data
This addresses the lack of ground-truth data for remote sensing stereo estimation, though it is incremental as it builds on existing self-supervised methods.
The paper tackles the problem of expensive ground-truth data for stereo estimation in remote sensing by proposing a self-supervised CNN with adaptive pseudo ground-truth, achieving improved disparity maps through iterative refinement.
Stereo estimation has made many advancements in recent years with the introduction of deep-learning. However the traditional supervised approach to deep-learning requires the creation of accurate and plentiful ground-truth data, which is expensive to create and not available in many situations. This is especially true for remote sensing applications, where there is an excess of available data without proper ground truth. To tackle this problem, we propose a self-supervised CNN with self-improving adaptive abilities. In the first iteration, the created disparity map is inaccurate and noisy. Leveraging the left-right consistency check, we get a sparse but more accurate disparity map which is used as an initial pseudo ground-truth. This pseudo ground-truth is then adapted and updated after every epoch in the training step of the network. We use the sum of inconsistent points in order to track the network convergence. The code for our method is publicly available at: https://github.com/thedodo/SAda-Net}{https://github.com/thedodo/SAda-Net