Virtual view rendering using super-resolution with multiview images

Bumsub Ham, Dongbo Min, Jinwook Choi, Kwanghoon Sohn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper presents a new approach to solve the problem of quality degradation of a synthesized view, when a virtual camera moves forward. Interpolation techniques using only two neighboring views are generally applied when a virtual view is synthesized. Because the size of an object increases when the virtual camera moves forward, conventional methods have usually addressed this problem by interpolation techniques in order to synthesize a virtual view. However, as it generates a degraded view such as blurred images, we prevent a synthesized view from being blurred by using more images in multiview camera configuration. That is, this problem is solved by applying super-resolution concept which reconstructs a high resolution image from several low resolution images. Data fusion is performed by geometric warping with disparity maps of the multiple images followed by deblurring. Experimental results show that the image quality can further be improved by reducing blurring and halo effects in comparison with the interpolation method.

Original languageEnglish
Title of host publication2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings
PublisherIEEE Computer Society
Pages2345-2348
Number of pages4
ISBN (Print)9781424456543
DOIs
Publication statusPublished - 2009 Jan 1
Event2009 IEEE International Conference on Image Processing, ICIP 2009 - Cairo, Egypt
Duration: 2009 Nov 72009 Nov 10

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Other

Other2009 IEEE International Conference on Image Processing, ICIP 2009
CountryEgypt
CityCairo
Period09/11/709/11/10

Fingerprint

Interpolation
Cameras
Image resolution
Optical resolving power
Data fusion
Image quality
Degradation

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Ham, B., Min, D., Choi, J., & Sohn, K. (2009). Virtual view rendering using super-resolution with multiview images. In 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings (pp. 2345-2348). [5414509] (Proceedings - International Conference on Image Processing, ICIP). IEEE Computer Society. https://doi.org/10.1109/ICIP.2009.5414509
Ham, Bumsub ; Min, Dongbo ; Choi, Jinwook ; Sohn, Kwanghoon. / Virtual view rendering using super-resolution with multiview images. 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings. IEEE Computer Society, 2009. pp. 2345-2348 (Proceedings - International Conference on Image Processing, ICIP).
@inproceedings{350c0bf348544f34b4a90ceda30e3480,
title = "Virtual view rendering using super-resolution with multiview images",
abstract = "This paper presents a new approach to solve the problem of quality degradation of a synthesized view, when a virtual camera moves forward. Interpolation techniques using only two neighboring views are generally applied when a virtual view is synthesized. Because the size of an object increases when the virtual camera moves forward, conventional methods have usually addressed this problem by interpolation techniques in order to synthesize a virtual view. However, as it generates a degraded view such as blurred images, we prevent a synthesized view from being blurred by using more images in multiview camera configuration. That is, this problem is solved by applying super-resolution concept which reconstructs a high resolution image from several low resolution images. Data fusion is performed by geometric warping with disparity maps of the multiple images followed by deblurring. Experimental results show that the image quality can further be improved by reducing blurring and halo effects in comparison with the interpolation method.",
author = "Bumsub Ham and Dongbo Min and Jinwook Choi and Kwanghoon Sohn",
year = "2009",
month = "1",
day = "1",
doi = "10.1109/ICIP.2009.5414509",
language = "English",
isbn = "9781424456543",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "2345--2348",
booktitle = "2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings",
address = "United States",

}

Ham, B, Min, D, Choi, J & Sohn, K 2009, Virtual view rendering using super-resolution with multiview images. in 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings., 5414509, Proceedings - International Conference on Image Processing, ICIP, IEEE Computer Society, pp. 2345-2348, 2009 IEEE International Conference on Image Processing, ICIP 2009, Cairo, Egypt, 09/11/7. https://doi.org/10.1109/ICIP.2009.5414509

Virtual view rendering using super-resolution with multiview images. / Ham, Bumsub; Min, Dongbo; Choi, Jinwook; Sohn, Kwanghoon.

2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings. IEEE Computer Society, 2009. p. 2345-2348 5414509 (Proceedings - International Conference on Image Processing, ICIP).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Virtual view rendering using super-resolution with multiview images

AU - Ham, Bumsub

AU - Min, Dongbo

AU - Choi, Jinwook

AU - Sohn, Kwanghoon

PY - 2009/1/1

Y1 - 2009/1/1

N2 - This paper presents a new approach to solve the problem of quality degradation of a synthesized view, when a virtual camera moves forward. Interpolation techniques using only two neighboring views are generally applied when a virtual view is synthesized. Because the size of an object increases when the virtual camera moves forward, conventional methods have usually addressed this problem by interpolation techniques in order to synthesize a virtual view. However, as it generates a degraded view such as blurred images, we prevent a synthesized view from being blurred by using more images in multiview camera configuration. That is, this problem is solved by applying super-resolution concept which reconstructs a high resolution image from several low resolution images. Data fusion is performed by geometric warping with disparity maps of the multiple images followed by deblurring. Experimental results show that the image quality can further be improved by reducing blurring and halo effects in comparison with the interpolation method.

AB - This paper presents a new approach to solve the problem of quality degradation of a synthesized view, when a virtual camera moves forward. Interpolation techniques using only two neighboring views are generally applied when a virtual view is synthesized. Because the size of an object increases when the virtual camera moves forward, conventional methods have usually addressed this problem by interpolation techniques in order to synthesize a virtual view. However, as it generates a degraded view such as blurred images, we prevent a synthesized view from being blurred by using more images in multiview camera configuration. That is, this problem is solved by applying super-resolution concept which reconstructs a high resolution image from several low resolution images. Data fusion is performed by geometric warping with disparity maps of the multiple images followed by deblurring. Experimental results show that the image quality can further be improved by reducing blurring and halo effects in comparison with the interpolation method.

UR - http://www.scopus.com/inward/record.url?scp=77951958958&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951958958&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2009.5414509

DO - 10.1109/ICIP.2009.5414509

M3 - Conference contribution

AN - SCOPUS:77951958958

SN - 9781424456543

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 2345

EP - 2348

BT - 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings

PB - IEEE Computer Society

ER -

Ham B, Min D, Choi J, Sohn K. Virtual view rendering using super-resolution with multiview images. In 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings. IEEE Computer Society. 2009. p. 2345-2348. 5414509. (Proceedings - International Conference on Image Processing, ICIP). https://doi.org/10.1109/ICIP.2009.5414509