论文标题
FIS网络：用于单眼估计的全图监督网络
FIS-Nets: Full-image Supervised Networks for Monocular Depth Estimation
论文作者
论文摘要
本文介绍了全图监督对单眼深度估计的重要性。我们提出了一个半监督的体系结构，该体系结构结合了使用图像一致性的无监督框架和密集深度完成的监督框架。后者提供了全图像的深度作为对前者的监督。导航系统中的自我动作也嵌入了无监督的框架中，作为内部时间变换网络的输出监督，使单眼深度估计更好。在评估中，我们表明我们提出的模型在深度估计上的表现优于其他方法。
This paper addresses the importance of full-image supervision for monocular depth estimation. We propose a semi-supervised architecture, which combines both unsupervised framework of using image consistency and supervised framework of dense depth completion. The latter provides full-image depth as supervision for the former. Ego-motion from navigation system is also embedded into the unsupervised framework as output supervision of an inner temporal transform network, making monocular depth estimation better. In the evaluation, we show that our proposed model outperforms other approaches on depth estimation.
