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.

本文提出了一种基于多尺度卷积神经网络、条件随机场及其连续形式的深度学习模型，用于单张静态图片的单目深度估计，该模型使用连续性的 CRF 完成深度估计，同时提出两个不同的变体，其中一个建立了多个 CRF 级联模型，另一个提出了一种结合模型；最后，作者在 NYUD-V2、Make3D 和 KITTI 等公共数据集上进行了大量实验，结果表明所提出方法得以有效地实现，并取得了目前最新的研究成果。

使用多尺度连续 CRFs 作为顺序深度网络进行单目深度估计

Monocular Depth Estimation using Multi-Scale Continuous CRFs as  Sequential Deep Networks

This paper addresses the problem of depth estimation from a single still
image. Inspired by 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, 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 extensive experimental evaluation
we demonstrate the effective- ness of the proposed approach and establish new
state of the art results on publicly available datasets.

本文提出了一种基于多尺度卷积神经网络（CNN）的深度模型，通过用连续条件随机场（CRF）融合多个 CNN 侧输出得到的互补信息。提出了两种不同的变体，一种基于多个 CRFs 级联，另一种基于统一的图模型，通过端到端的训练证明了效果显著，取得了公开数据集上的最新成果。