Presentation 2021-08-26
Unsupervised non-rigid alignment for multiple noisy images
Takanori Asanomi, Kazuya Nishimura, Heon Song, Junya Hayashida, Hiroyuki Sekiguchi, Takayuki Yagi, Imari Sato, Ryoma Bise,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a deep non-rigid alignment network that can simultaneously perform non-rigid alignment and noise decomposition of images despite severe noise and sparse errors. To address this challenging task, we introduce a low-rank loss in deep learning under the assumption that a batch of well-aligned and well-denoised images should be linearly correlated, and thus the matrix consisting the images should be low-lank. It allows us to remove the noise and corruption from input images in a self-supervised learning manner (i.e., t does not require any supervised data). In addition, we introduce a self-attention technique in order to aggregate the information about corruption from the batch of images. To the best of our knowledge, it is first attempt to introduce a low-rank loss for unsupervised deep alignment. Experiments using toy data and real medical image data demonstrate the effectiveness of the proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Unsupervised / Deep Learning / Alignment / Sparse complement
Paper # PRMU2021-7
Date of Issue 2021-08-19 (PRMU)

Conference Information
Committee PRMU
Conference Date 2021/8/26(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) CV/PR techniques for human-robot cooperation
Chair Seiichi Uchida(Kyushu Univ.)
Vice Chair Masakazu Iwamura(Osaka Pref. Univ.) / Mitsuru Anpai(Denso IT Lab.)
Secretary Masakazu Iwamura(NTT) / Mitsuru Anpai(Tottori Univ.)
Assistant Kouta Yamaguchi(CyberAgent) / Yusuke Matsui(Univ. of Tokyo)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding
Language ENG-JTITLE
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Unsupervised non-rigid alignment for multiple noisy images
Sub Title (in English)
Keyword(1) Unsupervised
Keyword(2) Deep Learning
Keyword(3) Alignment
Keyword(4) Sparse complement
1st Author's Name Takanori Asanomi
1st Author's Affiliation Kyushu University(Kyushu Univ.)
2nd Author's Name Kazuya Nishimura
2nd Author's Affiliation Kyushu University(Kyushu Univ.)
3rd Author's Name Heon Song
3rd Author's Affiliation Kyushu University(Kyushu Univ.)
4th Author's Name Junya Hayashida
4th Author's Affiliation Kyushu University(Kyushu Univ.)
5th Author's Name Hiroyuki Sekiguchi
5th Author's Affiliation Luxonus(Kyoto Univ.)
6th Author's Name Takayuki Yagi
6th Author's Affiliation Luxonus(Luxonus)
7th Author's Name Imari Sato
7th Author's Affiliation NII(NII)
8th Author's Name Ryoma Bise
8th Author's Affiliation Kyushu University(Kyushu Univ.)
Date 2021-08-26
Paper # PRMU2021-7
Volume (vol) vol.121
Number (no) PRMU-155
Page pp.pp.1-6(PRMU),
#Pages 6
Date of Issue 2021-08-19 (PRMU)