A Bayesian approach to shape from coded aperture

Manuel Martinello; Tom E. Bishop; Paolo Favaro

doi:10.1109/ICIP.2010.5653070

A Bayesian approach to shape from coded aperture

Manuel Martinello, Tom E. Bishop, Paolo Favaro

School of Engineering & Physical Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Citations (Scopus)

Abstract

In this paper we present analysis and a novel algorithm to estimate depth from a single image captured by a coded aperture camera. This is a challenging problem which requires new tools and investigations, compared with multi-view reconstruction. Unlike previous approaches, which need to recover both sharp image and depth, we consider directly estimating only depth, whilst still accounting for the statistics of the sharp image. The problem is formulated in a Bayesian framework, which enables us to reduce the estimation of the original sharp image to the local space-varying statistics of the texture. This yields an algorithm that can be solved via graph cuts (without user interaction). Performance and results on both synthetic and real data are reported and compared with previous methods. © 2010 IEEE.

Original language	English
Title of host publication	2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings
Pages	3521-3524
Number of pages	4
DOIs	https://doi.org/10.1109/ICIP.2010.5653070
Publication status	Published - 2010
Event	17th IEEE International Conference on Image Processing 2010 - Hong Kong, Hong Kong Duration: 26 Sept 2010 → 29 Sept 2010

Conference

Conference	17th IEEE International Conference on Image Processing 2010
Abbreviated title	ICIP 2010
Country/Territory	Hong Kong
City	Hong Kong
Period	26/09/10 → 29/09/10

Keywords

Bayesian methods
Coded aperture
Depth estimation
Single image

Access to Document

10.1109/ICIP.2010.5653070

Cite this

@inproceedings{0ad973caeea14255b9a410b499d16e47,

title = "A Bayesian approach to shape from coded aperture",

abstract = "In this paper we present analysis and a novel algorithm to estimate depth from a single image captured by a coded aperture camera. This is a challenging problem which requires new tools and investigations, compared with multi-view reconstruction. Unlike previous approaches, which need to recover both sharp image and depth, we consider directly estimating only depth, whilst still accounting for the statistics of the sharp image. The problem is formulated in a Bayesian framework, which enables us to reduce the estimation of the original sharp image to the local space-varying statistics of the texture. This yields an algorithm that can be solved via graph cuts (without user interaction). Performance and results on both synthetic and real data are reported and compared with previous methods. {\textcopyright} 2010 IEEE.",

keywords = "Bayesian methods, Coded aperture, Depth estimation, Single image",

author = "Manuel Martinello and Bishop, {Tom E.} and Paolo Favaro",

year = "2010",

doi = "10.1109/ICIP.2010.5653070",

language = "English",

isbn = "9781424479948",

pages = "3521--3524",

booktitle = "2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings",

note = "17th IEEE International Conference on Image Processing 2010, ICIP 2010 ; Conference date: 26-09-2010 Through 29-09-2010",

}

TY - GEN

T1 - A Bayesian approach to shape from coded aperture

AU - Martinello, Manuel

AU - Bishop, Tom E.

AU - Favaro, Paolo

PY - 2010

Y1 - 2010

N2 - In this paper we present analysis and a novel algorithm to estimate depth from a single image captured by a coded aperture camera. This is a challenging problem which requires new tools and investigations, compared with multi-view reconstruction. Unlike previous approaches, which need to recover both sharp image and depth, we consider directly estimating only depth, whilst still accounting for the statistics of the sharp image. The problem is formulated in a Bayesian framework, which enables us to reduce the estimation of the original sharp image to the local space-varying statistics of the texture. This yields an algorithm that can be solved via graph cuts (without user interaction). Performance and results on both synthetic and real data are reported and compared with previous methods. © 2010 IEEE.

AB - In this paper we present analysis and a novel algorithm to estimate depth from a single image captured by a coded aperture camera. This is a challenging problem which requires new tools and investigations, compared with multi-view reconstruction. Unlike previous approaches, which need to recover both sharp image and depth, we consider directly estimating only depth, whilst still accounting for the statistics of the sharp image. The problem is formulated in a Bayesian framework, which enables us to reduce the estimation of the original sharp image to the local space-varying statistics of the texture. This yields an algorithm that can be solved via graph cuts (without user interaction). Performance and results on both synthetic and real data are reported and compared with previous methods. © 2010 IEEE.

KW - Bayesian methods

KW - Coded aperture

KW - Depth estimation

KW - Single image

UR - http://www.scopus.com/inward/record.url?scp=78651105579&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2010.5653070

DO - 10.1109/ICIP.2010.5653070

M3 - Conference contribution

SN - 9781424479948

SP - 3521

EP - 3524

BT - 2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings

T2 - 17th IEEE International Conference on Image Processing 2010

Y2 - 26 September 2010 through 29 September 2010

ER -

A Bayesian approach to shape from coded aperture

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this