Video super-resolution using simultaneous motion and intensity calculations

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

Video super-resolution using simultaneous motion and intensity calculations. / Keller, Sune Høgild; Lauze, Francois Bernard; Nielsen, Mads.

I: IEEE Transactions on Image Processing, Bind 20, Nr. 7, 2011, s. 1870-1884.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Keller, SH, Lauze, FB & Nielsen, M 2011, 'Video super-resolution using simultaneous motion and intensity calculations', IEEE Transactions on Image Processing, bind 20, nr. 7, s. 1870-1884. https://doi.org/10.1109/TIP.2011.2106793

APA

Keller, S. H., Lauze, F. B., & Nielsen, M. (2011). Video super-resolution using simultaneous motion and intensity calculations. IEEE Transactions on Image Processing, 20(7), 1870-1884. https://doi.org/10.1109/TIP.2011.2106793

Vancouver

Keller SH, Lauze FB, Nielsen M. Video super-resolution using simultaneous motion and intensity calculations. IEEE Transactions on Image Processing. 2011;20(7):1870-1884. https://doi.org/10.1109/TIP.2011.2106793

Author

Keller, Sune Høgild ; Lauze, Francois Bernard ; Nielsen, Mads. / Video super-resolution using simultaneous motion and intensity calculations. I: IEEE Transactions on Image Processing. 2011 ; Bind 20, Nr. 7. s. 1870-1884.

Bibtex

@article{2b489ec9b635443aabf76e69aa4d7798,
title = "Video super-resolution using simultaneous motion and intensity calculations",
abstract = "In this paper we propose an energy based algorithm for motion compensated video super-resolution (VSR) targeted on upscaling of standard definition (SD) video to high definition (HD) video. Since the motion (flow field) of the image sequence is generally unknown, we introduce a formulation for the joint estimation of a super-resolution sequence and its flow field. Via the calculus of variations, this leads to a coupled system of partial differential equations for image sequence and motion estimation. We solve a simplified form of this system and as a by-product we indeed provide a motion field for super-resolved sequences. Computing super-resolved flows has to our knowledge not been done before. Most advanced super-resolution (SR) methods found in literature cannot be applied to general video with arbitrary scene content and/or arbitrary optical flows, as it is possible with our simultaneous VSR method. Series of experiments show that our method outperforms other VSR methods when dealing with general video input and that it continues to provide good results even for large scaling factors, up to 8×8.",
keywords = "Faculty of Science",
author = "Keller, {Sune H{\o}gild} and Lauze, {Francois Bernard} and Mads Nielsen",
year = "2011",
doi = "10.1109/TIP.2011.2106793",
language = "English",
volume = "20",
pages = "1870--1884",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers",
number = "7",

}

RIS

TY - JOUR

T1 - Video super-resolution using simultaneous motion and intensity calculations

AU - Keller, Sune Høgild

AU - Lauze, Francois Bernard

AU - Nielsen, Mads

PY - 2011

Y1 - 2011

N2 - In this paper we propose an energy based algorithm for motion compensated video super-resolution (VSR) targeted on upscaling of standard definition (SD) video to high definition (HD) video. Since the motion (flow field) of the image sequence is generally unknown, we introduce a formulation for the joint estimation of a super-resolution sequence and its flow field. Via the calculus of variations, this leads to a coupled system of partial differential equations for image sequence and motion estimation. We solve a simplified form of this system and as a by-product we indeed provide a motion field for super-resolved sequences. Computing super-resolved flows has to our knowledge not been done before. Most advanced super-resolution (SR) methods found in literature cannot be applied to general video with arbitrary scene content and/or arbitrary optical flows, as it is possible with our simultaneous VSR method. Series of experiments show that our method outperforms other VSR methods when dealing with general video input and that it continues to provide good results even for large scaling factors, up to 8×8.

AB - In this paper we propose an energy based algorithm for motion compensated video super-resolution (VSR) targeted on upscaling of standard definition (SD) video to high definition (HD) video. Since the motion (flow field) of the image sequence is generally unknown, we introduce a formulation for the joint estimation of a super-resolution sequence and its flow field. Via the calculus of variations, this leads to a coupled system of partial differential equations for image sequence and motion estimation. We solve a simplified form of this system and as a by-product we indeed provide a motion field for super-resolved sequences. Computing super-resolved flows has to our knowledge not been done before. Most advanced super-resolution (SR) methods found in literature cannot be applied to general video with arbitrary scene content and/or arbitrary optical flows, as it is possible with our simultaneous VSR method. Series of experiments show that our method outperforms other VSR methods when dealing with general video input and that it continues to provide good results even for large scaling factors, up to 8×8.

KW - Faculty of Science

U2 - 10.1109/TIP.2011.2106793

DO - 10.1109/TIP.2011.2106793

M3 - Journal article

C2 - 21245009

VL - 20

SP - 1870

EP - 1884

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 7

ER -

ID: 32339373