Depth cues have been proved very useful in various computer vision and robotic tasks. This paper addresses the problem of monocular depth estimation from a single still image. Inspired by the effectiveness of recent works on multi-scale convolutional neural networks (CNN), we propose a deep model which fuses complementary information derived from multiple CNN side outputs. Different from previous methods using concatenation or weighted average schemes, the integration is obtained by means of continuous Conditional Random Fields (CRFs). In particular, we propose two different variations, one based on a cascade of multiple CRFs, the other on a unified graphical model. By designing a novel CNN implementation of mean-field updates for continuous CRFs, we show that both proposed models can be regarded as sequential deep networks and that training can be performed end-to-end. Through an extensive experimental evaluation, we demonstrate the effectiveness of the proposed approach and establish new state of the art results for the monocular depth estimation task on three publicly available datasets, i.e., NYUD-V2, Make3D and KITTI.

中文翻译：

---

使用多尺度连续条件随机场作为序列深度网络的单目深度估计


深度线索已被证明在各种计算机视觉和机器人任务中非常有用。本文解决了从单个静止图像进行单眼深度估计的问题。受到近期多尺度卷积神经网络 (CNN) 工作有效性的启发，我们提出了一种深度模型，该模型融合了从多个 CNN 侧输出导出的互补信息。与以前使用级联或加权平均方案的方法不同，积分是通过连续条件随机场（CRF）获得的。特别是，我们提出了两种不同的变体，一种基于多个 CRF 的级联，另一种基于统一的图形模型。通过设计一种新颖的 CNN 实现连续条件随机场的平均场更新，我们表明所提出的两种模型都可以被视为顺序深度网络，并且可以端到端地进行训练。通过广泛的实验评估，我们证明了所提出方法的有效性，并在三个公开数据集（即 NYUD-V2、Make3D 和 KITTI）上为单目深度估计任务建立了新的最先进结果。