Sparsity based depth estimation and hole-filling algorithm for 2D to 3D video conversion

Jangwon Choi, Yoonsik Choe, Yong Goo Kim

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

4 Citations (Scopus)

Abstract

Depth image-based rendering (DIBR) requires to efficiently fill out holes in rendered image, and this has a great impact on the quality of 3D depth perception. In this paper, we propose a hole-filling method using depth estimation and image inpainting for high quality 3D video. In this algorithm, we first generate rendered image and its associated depth map. Then, we estimate the depths in generated depth map's hole. Using these values, we fill out the hole with depth-aided image inpainting based on the sparsity of hole. This method enables the inpainting to refer similar background texture. The proposed algorithm also fills out the patches of hole based on an edge-preserving priority, so that background edges of the image texture can be reconstructed faithfully. Experimental results show that the proposed algorithm provides better objective and subjective quality than previous works.

Original languageEnglish
Title of host publication2012 International Conference on Signals and Electronic Systems, ICSES 2012 - The Conference Proceedings
DOIs
Publication statusPublished - 2012 Dec 1
Event2012 International Conference on Signals and Electronic Systems, ICSES 2012 - Wroclaw, Poland
Duration: 2012 Sep 182012 Sep 21

Other

Other2012 International Conference on Signals and Electronic Systems, ICSES 2012
CountryPoland
CityWroclaw
Period12/9/1812/9/21

Fingerprint

Depth perception
Image texture
Textures

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Choi, J., Choe, Y., & Kim, Y. G. (2012). Sparsity based depth estimation and hole-filling algorithm for 2D to 3D video conversion. In 2012 International Conference on Signals and Electronic Systems, ICSES 2012 - The Conference Proceedings [6382254] https://doi.org/10.1109/ICSES.2012.6382254
Choi, Jangwon ; Choe, Yoonsik ; Kim, Yong Goo. / Sparsity based depth estimation and hole-filling algorithm for 2D to 3D video conversion. 2012 International Conference on Signals and Electronic Systems, ICSES 2012 - The Conference Proceedings. 2012.
@inproceedings{949477f521e54e9db913e75592cc9a4e,
title = "Sparsity based depth estimation and hole-filling algorithm for 2D to 3D video conversion",
abstract = "Depth image-based rendering (DIBR) requires to efficiently fill out holes in rendered image, and this has a great impact on the quality of 3D depth perception. In this paper, we propose a hole-filling method using depth estimation and image inpainting for high quality 3D video. In this algorithm, we first generate rendered image and its associated depth map. Then, we estimate the depths in generated depth map's hole. Using these values, we fill out the hole with depth-aided image inpainting based on the sparsity of hole. This method enables the inpainting to refer similar background texture. The proposed algorithm also fills out the patches of hole based on an edge-preserving priority, so that background edges of the image texture can be reconstructed faithfully. Experimental results show that the proposed algorithm provides better objective and subjective quality than previous works.",
author = "Jangwon Choi and Yoonsik Choe and Kim, {Yong Goo}",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/ICSES.2012.6382254",
language = "English",
isbn = "9781467317092",
booktitle = "2012 International Conference on Signals and Electronic Systems, ICSES 2012 - The Conference Proceedings",

}

Choi, J, Choe, Y & Kim, YG 2012, Sparsity based depth estimation and hole-filling algorithm for 2D to 3D video conversion. in 2012 International Conference on Signals and Electronic Systems, ICSES 2012 - The Conference Proceedings., 6382254, 2012 International Conference on Signals and Electronic Systems, ICSES 2012, Wroclaw, Poland, 12/9/18. https://doi.org/10.1109/ICSES.2012.6382254

Sparsity based depth estimation and hole-filling algorithm for 2D to 3D video conversion. / Choi, Jangwon; Choe, Yoonsik; Kim, Yong Goo.

2012 International Conference on Signals and Electronic Systems, ICSES 2012 - The Conference Proceedings. 2012. 6382254.

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

TY - GEN

T1 - Sparsity based depth estimation and hole-filling algorithm for 2D to 3D video conversion

AU - Choi, Jangwon

AU - Choe, Yoonsik

AU - Kim, Yong Goo

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Depth image-based rendering (DIBR) requires to efficiently fill out holes in rendered image, and this has a great impact on the quality of 3D depth perception. In this paper, we propose a hole-filling method using depth estimation and image inpainting for high quality 3D video. In this algorithm, we first generate rendered image and its associated depth map. Then, we estimate the depths in generated depth map's hole. Using these values, we fill out the hole with depth-aided image inpainting based on the sparsity of hole. This method enables the inpainting to refer similar background texture. The proposed algorithm also fills out the patches of hole based on an edge-preserving priority, so that background edges of the image texture can be reconstructed faithfully. Experimental results show that the proposed algorithm provides better objective and subjective quality than previous works.

AB - Depth image-based rendering (DIBR) requires to efficiently fill out holes in rendered image, and this has a great impact on the quality of 3D depth perception. In this paper, we propose a hole-filling method using depth estimation and image inpainting for high quality 3D video. In this algorithm, we first generate rendered image and its associated depth map. Then, we estimate the depths in generated depth map's hole. Using these values, we fill out the hole with depth-aided image inpainting based on the sparsity of hole. This method enables the inpainting to refer similar background texture. The proposed algorithm also fills out the patches of hole based on an edge-preserving priority, so that background edges of the image texture can be reconstructed faithfully. Experimental results show that the proposed algorithm provides better objective and subjective quality than previous works.

UR - http://www.scopus.com/inward/record.url?scp=84872371337&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872371337&partnerID=8YFLogxK

U2 - 10.1109/ICSES.2012.6382254

DO - 10.1109/ICSES.2012.6382254

M3 - Conference contribution

AN - SCOPUS:84872371337

SN - 9781467317092

BT - 2012 International Conference on Signals and Electronic Systems, ICSES 2012 - The Conference Proceedings

ER -

Choi J, Choe Y, Kim YG. Sparsity based depth estimation and hole-filling algorithm for 2D to 3D video conversion. In 2012 International Conference on Signals and Electronic Systems, ICSES 2012 - The Conference Proceedings. 2012. 6382254 https://doi.org/10.1109/ICSES.2012.6382254