Monocular Depth Estimation Using Multi-Scale Continuous CRFs as Sequential Deep Networks
Monocular Depth Estimation Using Multi-Scale Continuous CRFs as Sequential Deep Networks
复制标题
DOI：
10.1109/tpami.2018.2839602
复制
发表时间：
2018-03
影响因子：
23.6
通讯作者：
Dan Xu;E. Ricci;Wanli Ouyang;Xiaogang Wang;N. Sebe
中科院分区：
文献类型：
--
作者：
Dan Xu;E. Ricci;Wanli Ouyang;Xiaogang Wang;N. Sebe
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。本文研究了单幅静止图像的单目深度估计问题。受近期多尺度卷积神经网络（CNN）有效性研究的启发，我们提出了一种融合来自多个CNN侧输出的互补信息的深度模型。与以往采用串联或加权平均的方法不同，该方法采用连续条件随机场（CRFs）进行积分。特别地，我们提出了两种不同的变化，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crf的平均场更新，我们证明了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，并在三个公开可用的数据集（即NYUD-V2， Make3D和KITTI）上为单目深度估计任务建立了新的最新结果。
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.