Depth estimation from monocular color images using natural scene statistics models

Che-Chun Su, L. Cormack, A. Bovik
{"title":"Depth estimation from monocular color images using natural scene statistics models","authors":"Che-Chun Su, L. Cormack, A. Bovik","doi":"10.1109/IVMSPW.2013.6611900","DOIUrl":null,"url":null,"abstract":"We consider the problem of estimating a dense depth map from a single monocular image. Inspired by psychophysical evidence of visual processing in human vision systems (HVS) and natural scene statistics (NSS) models of image and range, we propose a Bayesian framework to recover detailed 3D scene structure by exploiting the statistical relationships between local image features and depth variations inherent in natural images. By observing that similar depth structures may exist in different types of luminance/chrominance textured regions in natural scenes, we build a dictionary of canonical range patterns as the prior, and fit a multivariate Gaussian mixture (MGM) model to associate local image features to different range patterns as the likelihood. Compared with the state-of-the-art depth estimation method, we achieve similar performance in terms of pixel-wise estimated range error, but superior capability of recovering relative distant relationships between different parts of the image.","PeriodicalId":170714,"journal":{"name":"IVMSP 2013","volume":"46 22 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IVMSP 2013","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IVMSPW.2013.6611900","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6

Abstract

We consider the problem of estimating a dense depth map from a single monocular image. Inspired by psychophysical evidence of visual processing in human vision systems (HVS) and natural scene statistics (NSS) models of image and range, we propose a Bayesian framework to recover detailed 3D scene structure by exploiting the statistical relationships between local image features and depth variations inherent in natural images. By observing that similar depth structures may exist in different types of luminance/chrominance textured regions in natural scenes, we build a dictionary of canonical range patterns as the prior, and fit a multivariate Gaussian mixture (MGM) model to associate local image features to different range patterns as the likelihood. Compared with the state-of-the-art depth estimation method, we achieve similar performance in terms of pixel-wise estimated range error, but superior capability of recovering relative distant relationships between different parts of the image.
基于自然场景统计模型的单眼彩色图像深度估计
我们考虑了从单眼图像估计密集深度图的问题。受人类视觉系统(HVS)中视觉处理的心理物理证据和图像和范围的自然场景统计(NSS)模型的启发,我们提出了一个贝叶斯框架,通过利用自然图像固有的局部图像特征和深度变化之间的统计关系来恢复详细的3D场景结构。通过观察自然场景中不同类型的亮度/色度纹理区域可能存在相似的深度结构,我们构建了典型范围模式字典作为先验,并拟合了多元高斯混合(MGM)模型,将局部图像特征与不同范围模式作为似然关联。与最先进的深度估计方法相比,我们在像素估计范围误差方面实现了类似的性能,但在恢复图像不同部分之间相对距离关系方面的能力更强。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信