GPU-friendly Approximate Bilateral Filter for 3D Volume Data

研究成果: Conference contribution

抄録

This paper presents an approximate Bilateral Filter(BF) with a GPU-friendly architecture for 3D volume data. The bilateral filter (BF) for 3D volume data such as medical images highly costs due to an enormous number of voxels to be processed. Existing acceleration methods called constant-time, or O(1), BF are inappropriate for GPU processing because they consist of a combination of O(1) spatial filters not to fit to parallel processing. The proposed method realizes a fast approximation 3D-BF by focusing two points: (1) the BF is decomposed into multiple Gaussian Filters and (2) GPU processing is suitable for convolution. As a consequence, proposed method achieved fast and high approximate accuracy in various window size.

元の言語English
ホスト出版物のタイトル2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings
出版者Institute of Electrical and Electronics Engineers Inc.
ページ2054-2058
ページ数5
ISBN(電子版)9789881476852
DOI
出版物ステータスPublished - 2019 3 4
イベント10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Honolulu, United States
継続期間: 2018 11 122018 11 15

出版物シリーズ

名前2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings

Conference

Conference10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018
United States
Honolulu
期間18/11/1218/11/15

Fingerprint

Processing
Convolution
Graphics processing unit
Costs

ASJC Scopus subject areas

  • Information Systems

これを引用

Yano, K., Sugimoto, K., & Kamata, S. (2019). GPU-friendly Approximate Bilateral Filter for 3D Volume Data. : 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings (pp. 2054-2058). [8659773] (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/APSIPA.2018.8659773

GPU-friendly Approximate Bilateral Filter for 3D Volume Data. / Yano, Koichi; Sugimoto, Kenjiro; Kamata, Seiichiro.

2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 2054-2058 8659773 (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings).

研究成果: Conference contribution

Yano, K, Sugimoto, K & Kamata, S 2019, GPU-friendly Approximate Bilateral Filter for 3D Volume Data. : 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings., 8659773, 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 2054-2058, 10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018, Honolulu, United States, 18/11/12. https://doi.org/10.23919/APSIPA.2018.8659773
Yano K, Sugimoto K, Kamata S. GPU-friendly Approximate Bilateral Filter for 3D Volume Data. : 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 2054-2058. 8659773. (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings). https://doi.org/10.23919/APSIPA.2018.8659773
Yano, Koichi ; Sugimoto, Kenjiro ; Kamata, Seiichiro. / GPU-friendly Approximate Bilateral Filter for 3D Volume Data. 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 2054-2058 (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings).
@inproceedings{1ca13885417e4dc6a32a21848bf4ebcd,
title = "GPU-friendly Approximate Bilateral Filter for 3D Volume Data",
abstract = "This paper presents an approximate Bilateral Filter(BF) with a GPU-friendly architecture for 3D volume data. The bilateral filter (BF) for 3D volume data such as medical images highly costs due to an enormous number of voxels to be processed. Existing acceleration methods called constant-time, or O(1), BF are inappropriate for GPU processing because they consist of a combination of O(1) spatial filters not to fit to parallel processing. The proposed method realizes a fast approximation 3D-BF by focusing two points: (1) the BF is decomposed into multiple Gaussian Filters and (2) GPU processing is suitable for convolution. As a consequence, proposed method achieved fast and high approximate accuracy in various window size.",
author = "Koichi Yano and Kenjiro Sugimoto and Seiichiro Kamata",
year = "2019",
month = "3",
day = "4",
doi = "10.23919/APSIPA.2018.8659773",
language = "English",
series = "2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2054--2058",
booktitle = "2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings",

}

TY - GEN

T1 - GPU-friendly Approximate Bilateral Filter for 3D Volume Data

AU - Yano, Koichi

AU - Sugimoto, Kenjiro

AU - Kamata, Seiichiro

PY - 2019/3/4

Y1 - 2019/3/4

N2 - This paper presents an approximate Bilateral Filter(BF) with a GPU-friendly architecture for 3D volume data. The bilateral filter (BF) for 3D volume data such as medical images highly costs due to an enormous number of voxels to be processed. Existing acceleration methods called constant-time, or O(1), BF are inappropriate for GPU processing because they consist of a combination of O(1) spatial filters not to fit to parallel processing. The proposed method realizes a fast approximation 3D-BF by focusing two points: (1) the BF is decomposed into multiple Gaussian Filters and (2) GPU processing is suitable for convolution. As a consequence, proposed method achieved fast and high approximate accuracy in various window size.

AB - This paper presents an approximate Bilateral Filter(BF) with a GPU-friendly architecture for 3D volume data. The bilateral filter (BF) for 3D volume data such as medical images highly costs due to an enormous number of voxels to be processed. Existing acceleration methods called constant-time, or O(1), BF are inappropriate for GPU processing because they consist of a combination of O(1) spatial filters not to fit to parallel processing. The proposed method realizes a fast approximation 3D-BF by focusing two points: (1) the BF is decomposed into multiple Gaussian Filters and (2) GPU processing is suitable for convolution. As a consequence, proposed method achieved fast and high approximate accuracy in various window size.

UR - http://www.scopus.com/inward/record.url?scp=85063534280&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063534280&partnerID=8YFLogxK

U2 - 10.23919/APSIPA.2018.8659773

DO - 10.23919/APSIPA.2018.8659773

M3 - Conference contribution

AN - SCOPUS:85063534280

T3 - 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings

SP - 2054

EP - 2058

BT - 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -