arrow
返回

A contextual conditional random field network for monocular depth estimation

delete2020-06-01
delete5
PRE
AI
J
Jun Liu
Q
Qing Li
R
Rui Cao
唐
唐文明 (Wenming Tang)
G
Guoping Qiu *
DOI:10.1016/j.imavis.2020.103922delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Monocular depth estimation plays a crucial role in understanding 3D scene geometry and is a challenging computer vision task. Recently, deep convolutional neural networks have been applied to solve this problem. However, existing methods either directly exploiting RGB pixels which can introduce much noise into the depth map or utilizing over smoothed internal representation features which can cause blur in the depth map. In this paper, we propose a contextual CRF network (CCN) to tackle these issues. The new CCN adopts the popular encoder-decoder architecture with a new contextual CRF module (CCM) which is guided by the depth features and regularizes the information flow from the encoder layer to the corresponding layer in the decoder, thus can reduce the mismatch between the RGB pixel and the depth map cue while at the same time retain detail features to output a fine-grained depth map. Moreover, we propose a depth-guided loss function which pays a balanced attention to near and far pixels thus addressing the long-tailed distribution of depth information. We have conducted extensive experiments on three public datasets for monocular depth estimation. Results demonstrate that our proposed CCN achieves superior performances in terms of visual quality and competitive quantitative results when compared with state-of-the-art methods. (C) 2020 Elsevier B.V. All rights reserved.
Keyword:
Monocular depth estimation
Deep neural network
Skip connection
Conditional random field
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Image and Vision Computing 封面图
Image and Vision Computing
IF:
4.2
论文数:
4.1K
被引数:
6.7K

机构

S
shenzhen university
学者数:
4.6W
论文数: 3.4W
被引数: 72
引用论文

引用论文

Fortification in Beverages
err2019-01-01
err0
PREAI
errAsif Ahmad; Zaheer Ahmed
err分享
err收藏
Automatic photo pop-up
err2005-07-01
err467
PREAI
errHoiem, D; Efros, AA; Hebert, M
err分享
err收藏
没有更多内容