Despite the success of deep learning in disparity estimation, the domain generalization gap remains an issue. We propose a semi-supervised pipeline that successfully adapts DispNet to a real-world domain by joint supervised training on labeled synthetic data and self-supervised training on unlabeled real data. Furthermore, accounting for the limitations of the widely-used photometric loss, we analyze the impact of deep feature reconstruction as a promising supervisory signal for disparity estimation.

翻译：尽管在差异估计方面的深层学习取得了成功,但广域化差距仍然是一个问题。 我们提议建立一个半监督的管道,通过在标签合成数据和未标签真实数据方面进行联合监督培训和自我监督培训,使DispNet成功适应现实世界领域。 此外,考虑到广泛使用的光度测量损失的局限性,我们分析深地貌重建的影响,将其作为悬殊估计的一个有希望的监督信号。