Dense correspondence based prediction for image set compression

Yabin  Zhang; Weisi Lin; Jianfei Cai

doi:10.1109/ICASSP.2015.7178168

Dense correspondence based prediction for image set compression

Yabin Zhang, Weisi Lin, Jianfei Cai

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

3 Citations (Scopus)

Abstract

In this paper, we propose a novel dense correspondence based prediction approach to reduce the inter-image redundancy for image set compression. Unlike previous methods, we manage to utilize the dense correspondence to predict and parameterize the inter-image relation and then reconstruct a new reference for the subsequent HEVC inter-prediction and encoding. Comparing to relevant state-of-the-art feature-based methods, our method is able to locally approximate the inter-image relation and thus more robust to complex local variations. Experimental results show that our proposed approach achieves better coding gains when the local variations are dominant.

Original language	English
Title of host publication	2015 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings
Editors	Doug Gray, Doug Cochran
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	1240-1244
Number of pages	5
ISBN (Electronic)	9781467369978
DOIs	https://doi.org/10.1109/ICASSP.2015.7178168
Publication status	Published - 2015
Externally published	Yes
Event	IEEE International Conference on Acoustics, Speech and Signal Processing 2015 - Brisbane Convention & Exhibition Centre, Brisbane, Australia Duration: 19 Apr 2015 → 24 Apr 2015 https://ieeexplore.ieee.org/xpl/conhome/7158221/proceeding (Proceedings)

Conference

Conference	IEEE International Conference on Acoustics, Speech and Signal Processing 2015
Abbreviated title	ICASSP 2015
Country/Territory	Australia
City	Brisbane
Period	19/04/15 → 24/04/15
Internet address	https://ieeexplore.ieee.org/xpl/conhome/7158221/proceeding (Proceedings)

Keywords

Dense correspondence based prediction
HEVC
image set compression
reference reconstruction

Access to Document

10.1109/ICASSP.2015.7178168

Cite this

@inproceedings{7f20f1e43f00490ca5b9d2be123c9126,

title = "Dense correspondence based prediction for image set compression",

abstract = "In this paper, we propose a novel dense correspondence based prediction approach to reduce the inter-image redundancy for image set compression. Unlike previous methods, we manage to utilize the dense correspondence to predict and parameterize the inter-image relation and then reconstruct a new reference for the subsequent HEVC inter-prediction and encoding. Comparing to relevant state-of-the-art feature-based methods, our method is able to locally approximate the inter-image relation and thus more robust to complex local variations. Experimental results show that our proposed approach achieves better coding gains when the local variations are dominant.",

keywords = "Dense correspondence based prediction, HEVC, image set compression, reference reconstruction",

author = "Yabin Zhang and Weisi Lin and Jianfei Cai",

year = "2015",

doi = "10.1109/ICASSP.2015.7178168",

language = "English",

pages = "1240--1244",

editor = "Gray, {Doug } and Cochran, {Doug }",

booktitle = "2015 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "IEEE International Conference on Acoustics, Speech and Signal Processing 2015, ICASSP 2015 ; Conference date: 19-04-2015 Through 24-04-2015",

url = "https://ieeexplore.ieee.org/xpl/conhome/7158221/proceeding",

}

Zhang, Y, Lin, W & Cai, J 2015, Dense correspondence based prediction for image set compression. in D Gray & D Cochran (eds), 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings., 7178168, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 1240-1244, IEEE International Conference on Acoustics, Speech and Signal Processing 2015, Brisbane, Queensland, Australia, 19/04/15. https://doi.org/10.1109/ICASSP.2015.7178168

Dense correspondence based prediction for image set compression. / Zhang, Yabin ; Lin, Weisi; Cai, Jianfei.

2015 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings. ed. / Doug Gray; Doug Cochran. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2015. p. 1240-1244 7178168.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Dense correspondence based prediction for image set compression

AU - Zhang, Yabin

AU - Lin, Weisi

AU - Cai, Jianfei

PY - 2015

Y1 - 2015

N2 - In this paper, we propose a novel dense correspondence based prediction approach to reduce the inter-image redundancy for image set compression. Unlike previous methods, we manage to utilize the dense correspondence to predict and parameterize the inter-image relation and then reconstruct a new reference for the subsequent HEVC inter-prediction and encoding. Comparing to relevant state-of-the-art feature-based methods, our method is able to locally approximate the inter-image relation and thus more robust to complex local variations. Experimental results show that our proposed approach achieves better coding gains when the local variations are dominant.

AB - In this paper, we propose a novel dense correspondence based prediction approach to reduce the inter-image redundancy for image set compression. Unlike previous methods, we manage to utilize the dense correspondence to predict and parameterize the inter-image relation and then reconstruct a new reference for the subsequent HEVC inter-prediction and encoding. Comparing to relevant state-of-the-art feature-based methods, our method is able to locally approximate the inter-image relation and thus more robust to complex local variations. Experimental results show that our proposed approach achieves better coding gains when the local variations are dominant.

KW - Dense correspondence based prediction

KW - HEVC

KW - image set compression

KW - reference reconstruction

UR - http://www.scopus.com/inward/record.url?scp=84946013945&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2015.7178168

DO - 10.1109/ICASSP.2015.7178168

M3 - Conference Paper

AN - SCOPUS:84946013945

SP - 1240

EP - 1244

BT - 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings

A2 - Gray, Doug

A2 - Cochran, Doug

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

T2 - IEEE International Conference on Acoustics, Speech and Signal Processing 2015

Y2 - 19 April 2015 through 24 April 2015

ER -

Dense correspondence based prediction for image set compression

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this