Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

A Coding-Cost Framework for Super-Resolution Motion Layer Decomposition

Schoenemann, Thomas LU and Cremers, Daniel (2012) In IEEE Transactions on Image Processing 21(3). p.1097-1110
Abstract
We consider the problem of decomposing a video sequence into a superposition of (a given number of) moving layers. For this problem, we propose an energy minimization approach based on the coding cost. Our contributions affect both the model (what is minimized) and the algorithmic side (how it is minimized). The novelty of the coding-cost model is the inclusion of a refined model of the image formation process, known as super resolution. This accounts for camera blur and area averaging arising in a physically plausible image formation process. It allows us to extract sharp high-resolution layers from the video sequence. The algorithmic framework is based on an alternating minimization scheme and includes the following innovations. 1) A... (More)
We consider the problem of decomposing a video sequence into a superposition of (a given number of) moving layers. For this problem, we propose an energy minimization approach based on the coding cost. Our contributions affect both the model (what is minimized) and the algorithmic side (how it is minimized). The novelty of the coding-cost model is the inclusion of a refined model of the image formation process, known as super resolution. This accounts for camera blur and area averaging arising in a physically plausible image formation process. It allows us to extract sharp high-resolution layers from the video sequence. The algorithmic framework is based on an alternating minimization scheme and includes the following innovations. 1) A video labeling, we optimize the layer domains. This allows to regularize the shapes of the layers and a very elegant handling of occlusions. 2) We present an efficient parallel algorithm for extracting super-resolved layers based on TV filtering. (Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Image decomposition, image motion analysis, optimization, video signal, processing
in
IEEE Transactions on Image Processing
volume
21
issue
3
pages
1097 - 1110
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
external identifiers
  • wos:000300510800016
  • scopus:84857311375
  • pmid:21947524
ISSN
1941-0042
DOI
10.1109/TIP.2011.2169271
language
English
LU publication?
yes
id
e26b5733-2d2d-4943-9846-f8169d30f143 (old id 2390904)
date added to LUP
2016-04-01 11:10:37
date last changed
2022-01-26 06:01:38
@article{e26b5733-2d2d-4943-9846-f8169d30f143,
  abstract     = {{We consider the problem of decomposing a video sequence into a superposition of (a given number of) moving layers. For this problem, we propose an energy minimization approach based on the coding cost. Our contributions affect both the model (what is minimized) and the algorithmic side (how it is minimized). The novelty of the coding-cost model is the inclusion of a refined model of the image formation process, known as super resolution. This accounts for camera blur and area averaging arising in a physically plausible image formation process. It allows us to extract sharp high-resolution layers from the video sequence. The algorithmic framework is based on an alternating minimization scheme and includes the following innovations. 1) A video labeling, we optimize the layer domains. This allows to regularize the shapes of the layers and a very elegant handling of occlusions. 2) We present an efficient parallel algorithm for extracting super-resolved layers based on TV filtering.}},
  author       = {{Schoenemann, Thomas and Cremers, Daniel}},
  issn         = {{1941-0042}},
  keywords     = {{Image decomposition; image motion analysis; optimization; video signal; processing}},
  language     = {{eng}},
  number       = {{3}},
  pages        = {{1097--1110}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  series       = {{IEEE Transactions on Image Processing}},
  title        = {{A Coding-Cost Framework for Super-Resolution Motion Layer Decomposition}},
  url          = {{http://dx.doi.org/10.1109/TIP.2011.2169271}},
  doi          = {{10.1109/TIP.2011.2169271}},
  volume       = {{21}},
  year         = {{2012}},
}