Presentation | 2022-02-21 2種類の露光画像からのハイダイナミックレンジ画像合成 Daichi Horita, Kiyoharu Aizawa, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The dynamic range of electronic imaging is orders of magnitudes smaller than that of human vision. To obtain images of high-contrast scenes, high dynamic range (HDR) reconstruction from multiple exposure images is necessary. In this paper, we propose an unsupervised learning framework for HDR reconstruction from only two differently exposed images. Our unsupervised learning framework converts existing HDR images to differently conditioned low dynamic range (LDR) images via camera pipelines and enables the learning of HDR reconstruction. We also propose an alignment module to handle changes in images that are not well-aligned because of different timings. To train our framework, we integrated and preprocessed existing HDR datasets to create a large dataset. We created a test dataset that consisted of a set of differently exposed LDR images of static scenes and their ground truth HDR images. We also created a set of LDR images for the dynamic scenes. Experiments demonstrated that our method outperformed the previous methods in quantitative and qualitative evaluations. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | High dynamic range image / Image-to-image translation / Unsupervised learning |
Paper # | ITS2021-28,IE2021-37 |
Date of Issue | 2022-02-14 (ITS, IE) |
Conference Information | |
Committee | IE / ITS / ITE-AIT / ITE-ME / ITE-MMS |
---|---|
Conference Date | 2022/2/21(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Image Processing, etc. |
Chair | Kazuya Kodama(NII) / Masahiro Fujii(Utsunomiya Univ.) / Hisaki Nate(Tokyo Polytechnic Univ.) / Hiroyuki Arai(Nippon Inst. of Tech.) / Kenji Machida(NHK) |
Vice Chair | Hiroyuki Bandoh(NTT) / Toshihiko Yamazaki(Univ. of Tokyo) / Kohei Ohno(Meiji Univ.) / Naohisa Hashimoto(AIST) / / Shogo Muramatsu(Niigata Univ.) |
Secretary | Hiroyuki Bandoh(KDDI Research) / Toshihiko Yamazaki(Nagoya Inst. of Tech.) / Kohei Ohno(Akita Prefectural Univ.) / Naohisa Hashimoto(NIT, Tsuruoka College) / / Shogo Muramatsu(NHK) / (Hokkaido Univ.) |
Assistant | Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT) / Msataka Imao(Mitsubishi Electric) / Kenshi Saho(Toyama Prefectural Univ.) / Keiji Jimi(Gunma Univ.) |
Paper Information | |
Registration To | Technical Committee on Image Engineering / Technical Committee on Intelligent Transport Systems Technology / Technical Group on Artistic Image Technology / Technical Group on Media Engineering / Technical Group on Multi-media Storage |
---|---|
Language | JPN-ONLY |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | |
Sub Title (in English) | |
Keyword(1) | High dynamic range image |
Keyword(2) | Image-to-image translation |
Keyword(3) | Unsupervised learning |
1st Author's Name | Daichi Horita |
1st Author's Affiliation | The University of Tokyo(Univ. of Tokyo) |
2nd Author's Name | Kiyoharu Aizawa |
2nd Author's Affiliation | The University of Tokyo(Univ. of Tokyo) |
Date | 2022-02-21 |
Paper # | ITS2021-28,IE2021-37 |
Volume (vol) | vol.121 |
Number (no) | ITS-373,IE-374 |
Page | pp.pp.19-24(ITS), pp.19-24(IE), |
#Pages | 6 |
Date of Issue | 2022-02-14 (ITS, IE) |