Unsupervised Stereo Matching Network For VHR Remote Sensing Images Based On Error Prediction

TL;DR

This paper introduces an unsupervised stereo matching network tailored for very-high-resolution remote sensing images, overcoming data limitations of supervised methods and demonstrating superior accuracy and generalization in experiments.

Contribution

A novel unsupervised stereo matching network with a confidence-error bridge module and robust loss functions for VHR remote sensing images.

Findings

Achieves superior accuracy over other unsupervised methods

Exhibits better generalization than supervised models

Demonstrates effectiveness on US3D and WHU-Stereo datasets

Abstract

Stereo matching in remote sensing has recently garnered increased attention, primarily focusing on supervised learning. However, datasets with ground truth generated by expensive airbone Lidar exhibit limited quantity and diversity, constraining the effectiveness of supervised networks. In contrast, unsupervised learning methods can leverage the increasing availability of very-high-resolution (VHR) remote sensing images, offering considerable potential in the realm of stereo matching. Motivated by this intuition, we propose a novel unsupervised stereo matching network for VHR remote sensing images. A light-weight module to bridge confidence with predicted error is introduced to refine the core model. Robust unsupervised losses are formulated to enhance network convergence. The experimental results on US3D and WHU-Stereo datasets demonstrate that the proposed network achieves superior accuracy compared to other unsupervised networks and exhibits better generalization capabilities than supervised models. Our code will be available at https://github.com/Elenairene/CBEM.