Recovering the scene depth from a single image is an ill-posed problem that
requires additional priors, often referred to as monocular depth cues, to
disambiguate different 3D interpretations. In recent works, those priors have
been learned in an end-to-end manner from large datasets b
本文提出了一种结构感知的神经网络来处理单目深度估计过程中普遍存在的结构信息缺失问题，该网络采用了空间注意力块来捕捉视觉特征的空间关系，引入全局聚焦相对损失来增强深度预测的空间约束，并引入了新的 Hard Case Depth 数据集和专门的渐进式训练策略来训练模型，实验证明该方法在 NYUDv2 数据集上具有很高的预测精度和泛化性能。