Monocular depth estimation and completion are fundamental aspects of geometric computer vision, serving as essential techniques for various downstream applications. In recent developments, several methods have reformulated these two tasks as a classification-regression problem, deriving depth with a linear combination of predicted probabilistic distribution and bin centers. In this paper, we introduce an innovative concept termed iterative elastic bins (IEBins) for the classification-regression-based monocular depth estimation and completion. The IEBins involves the idea of iterative division of bins. In the initialization stage, a coarse and uniform discretization is applied to the entire depth range. Subsequent update stages then iteratively identify and uniformly discretize the target bin, by leveraging it as the new depth range for further refinement. To mitigate the risk of error accumulation during iterations, we propose a novel elastic target bin, replacing the original one. The width of this elastic bin is dynamically adapted according to the depth uncertainty. Furthermore, we develop dedicated frameworks to instantiate the IEBins. Extensive experiments on the KITTI, NYU-Depth-v2, SUN RGB-D, ScanNet and DIODE datasets indicate that our method outperforms prior state-of-the-art monocular depth estimation and completion competitors.

单目深度估计和完成是几何计算机视觉的基本方面，是各种下游应用的基本技术。在最近的发展中，几种方法将这两个任务重新表述为分类回归问题，通过预测的概率分布和 bin 中心的线性组合来推导出深度。在本文中，我们引入了一个称为迭代弹性箱 （IEBins） 的创新概念，用于基于分类回归的单目深度估计和完成。IEBins 涉及 bin 迭代划分的思想。在初始化阶段，对整个深度范围应用粗略而均匀的离散化。然后，后续更新阶段迭代地识别并统一离散目标箱，将其用作新的深度范围以进行进一步细化。为了降低迭代过程中错误累积的风险，我们提出了一种新的弹性目标箱，取代了原来的目标箱。这个弹性箱的宽度会根据深度的不确定性动态调整。此外，我们还开发了专用框架来实例化 IEBins。在 KITTI、NYU-Depth-v2、SUN RGB-D、ScanNet 和 DIODE 数据集上的广泛实验表明，我们的方法优于以前最先进的单目深度估计和完成竞争对手。