Single image depth estimation is a challenging problem. The current state-of-the-art method formulates the problem as that of ordinal regression. However, the formulation is not fully differentiable and depth maps are not generated in an end-to-end fashion. The method uses a na\"ive threshold strategy to determine per-pixel depth labels, which results in significant discretization errors. For the first time, we formulate a fully differentiable ordinal regression and train the network in end-to-end fashion. This enables us to include boundary and smoothness constraints in the optimization function, leading to smooth and edge-consistent depth maps. A novel per-pixel confidence map computation for depth refinement is also proposed. Extensive evaluation of the proposed model on challenging benchmarks reveals its superiority over recent state-of-the-art methods, both quantitatively and qualitatively. Additionally, we demonstrate practical utility of the proposed method for single camera bokeh solution using in-house dataset of challenging real-life images.

中文翻译：

---

AcED：准确且边缘一致的单目深度估计

单幅图像深度估计是一个具有挑战性的问题。当前最先进的方法将问题表述为序数回归问题。然而，公式不是完全可微的，深度图不是以端到端的方式生成的。该方法使用朴素的阈值策略来确定每个像素的深度标签，这会导致显着的离散化错误。我们第一次制定了完全可微的序数回归并以端到端的方式训练网络。这使我们能够在优化函数中包含边界和平滑约束，从而产生平滑和边缘一致的深度图。还提出了一种用于深度细化的新的每像素置信度图计算。在具有挑战性的基准测试中对所提出的模型进行了广泛的评估，揭示了它在数量和质量上都优于最近最先进的方法。此外，我们使用具有挑战性的现实生活图像的内部数据集展示了所提出的单相机散景解决方案的实际效用。