Presentation | 2018-09-27 An Inverse Tone Mapping Operation Using CNN with LDR Based Learning Yuma Kinoshita, Hitoshi Kiya, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper proposes an inverse tone mapping operation using CNN with LDR based learning. In inverse tone mapping with CNNs, it is difficult to train CNNs by directly using HDR images as training data. In the proposed method, CNNs are trained with only LDR images, namely, HDR images are not used in training. The proposed CNNs learn a transformation from various input LDR images to LDR images mapped by Reinhard's global operator. Since Reinhard's global operator is invertible, HDR images can be reconstracted from LDR images mapped by the operator. For this reason, the proposed method enables us to generate high quality HDR images from various LDR images by transforming the input LDR ones via CNNs. Experimental results show that HDR images generated by the proposed method have higher quality than HDR ones generated by conventional inverse tone mapping methods, in terms of HDR-VDP-2.2 and PU encoding + MS-SSIM. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Inverse Tone Mapping / High Dynamic Range Image / Convolutional Neural Network / Deep Learning / Image Enhancement |
Paper # | LOIS2018-14,IE2018-34,EMM2018-53 |
Date of Issue | 2018-09-20 (LOIS, IE, EMM) |
Conference Information | |
Committee | IEE-CMN / EMM / LOIS / IE / ITE-ME |
---|---|
Conference Date | 2018/9/27(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Beppu Int'l Convention Ctr. aka B-CON Plaza |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Multimedia Communication/System, Lifelog Applications, IP Broadcasting/Video Transmission, Media Security, Media Processing (AI, Deep Learning), etc. |
Chair | Shun Morimura(CRIEPI) / Keiichi Iwamura(TUC) / Tomohiro Yamada(NTT) / Takayuki Hamamoto(Tokyo Univ. of Science) / Miki Haseyama(北大) |
Vice Chair | / Minoru Kuribayashi(Okayama Univ.) / Tetsuya Kojima(NIT,Tokyo College) / Toru Kobayashi(Nagasaki Univ.) / Hideaki Kimata(NTT) / Kazuya Kodama(NII) / Norio Tagawa(Tokyo Metropolitan Univ.) |
Secretary | (Tokai Univ.) / Minoru Kuribayashi(Kansai Univ.) / Tetsuya Kojima(NIT, Tokyo) / Toru Kobayashi(Chukyo Univ.) / Hideaki Kimata(NTT) / Kazuya Kodama(Research Organization of Information and Systems) / Norio Tagawa(KDDI Research) |
Assistant | Tomotaka Kimura(Doshisha Univ.) / 田中 彰浩(CRIEPI) / Hiroko Akiyama(NIT, Nagano College) / Kitahiro Kaneda(CANON) / Shinichiro Eitoku(NTT) / Kazuya Hayase(NTT) / Yasutaka Matsuo(NHK) |
Paper Information | |
Registration To | Technical Meeting on Communications / Technical Committee on Enriched MultiMedia / Technical Committee on Life Intelligence and Office Information Systems / Technical Committee on Image Engineering / Technical Group on Media Engineering |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | An Inverse Tone Mapping Operation Using CNN with LDR Based Learning |
Sub Title (in English) | |
Keyword(1) | Inverse Tone Mapping |
Keyword(2) | High Dynamic Range Image |
Keyword(3) | Convolutional Neural Network |
Keyword(4) | Deep Learning |
Keyword(5) | Image Enhancement |
1st Author's Name | Yuma Kinoshita |
1st Author's Affiliation | Tokyo Metropolitan University(Tokyo Metro. Univ.) |
2nd Author's Name | Hitoshi Kiya |
2nd Author's Affiliation | Tokyo Metropolitan University(Tokyo Metro. Univ.) |
Date | 2018-09-27 |
Paper # | LOIS2018-14,IE2018-34,EMM2018-53 |
Volume (vol) | vol.118 |
Number (no) | LOIS-222,IE-223,EMM-224 |
Page | pp.pp.23-28(LOIS), pp.23-28(IE), pp.23-28(EMM), |
#Pages | 6 |
Date of Issue | 2018-09-20 (LOIS, IE, EMM) |