| Presentation | 2017-03-06 A Study on HDR Image Generation Method from an SDR Image Using Deep Neural Networks Katsuhiko Hirao, Masaru Takeuchi, Jiro Katto, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we propose a deep learning method to generate an HDR image from a single SDR image with restoring over and under exposed regions. Firstly, as a preliminary experiment, we regard SDR images as pseudo HDR images, linearly reduce their dynamic ranges as pseudo SDR images, and then train DNN (Deep Neural Network) to generate the end-to-end mapping from pseudo SDR images to pseudo HDR images. Thereafter we show the effectivity of our method by PSNR evaluation. Secondly, as a main experiment, we generate SDR images from HDR images using tone mapping, then try to generate an HDR image from an SDR image using DNN. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Deep Learning / HDR / SDR / Image Restoration |
| Paper # | IMQ2016-26,IE2016-141,MVE2016-49 |
| Date of Issue | 2017-02-27 (IMQ, IE, MVE) |
| Conference Information | |
| Committee | MVE / IE / CQ / IMQ |
|---|---|
| Conference Date | 2017/3/6(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Kyusyu Univ. Ohashi Campus |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Five senses media, Multimedia, Virtual Environment, Image encoding, Ultra realistic, Network quality and reliability, Image media quality, etc. |
| Chair | Yoshinari Kameda(Univ. of Tsukuba) / Seishi Takamura(NTT) / Kyoko Yamori(Asahi Univ.) / Yuukou Horita(Univ. of Toyama) |
| Vice Chair | Kenji Mase(Nagoya Univ.) / Takayuki Hamamoto(Tokyo Univ. of Science) / Atsuro Ichigaya(NHK) / Takanori Hayashi(NTT) / Hideyuki Shimonishi(NEC) / Kenji Sugiyama(Seikei Univ.) / Toshiya Nakaguchi(Chiba Univ.) |
| Secretary | Kenji Mase(Kyushu Univ.) / Takayuki Hamamoto(Kyoto Univ.) / Atsuro Ichigaya(NTT) / Takanori Hayashi(NTT) / Hideyuki Shimonishi(Chiba Inst. of Tech.) / Kenji Sugiyama(Osaka Univ.) / Toshiya Nakaguchi(Keio Univ.) |
| Assistant | Hideaki Uchiyama(Kyushu Univ.) / Takatsugu Hirayama(Nagoya Univ.) / Ryosuke Aoki(NTT) / Kei Kawamura(KDDI R&D Labs.) / Keita Takahashi(Nagoya Univ.) / Hirantha Abeysekera(NTT) / Norihiro Fukumoto(KDDI R&D Labs.) / Shinichiro Saito(Sony) / Masaru Tsuchida(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Multimedia and Virtual Environment / Technical Committee on Image Engineering / Technical Committee on Communication Quality / Technical Committee on Image Media Quality |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Study on HDR Image Generation Method from an SDR Image Using Deep Neural Networks |
| Sub Title (in English) | |
| Keyword(1) | Deep Learning |
| Keyword(2) | HDR |
| Keyword(3) | SDR |
| Keyword(4) | Image Restoration |
| 1st Author's Name | Katsuhiko Hirao |
| 1st Author's Affiliation | Waseda University(Waseda Univ.) |
| 2nd Author's Name | Masaru Takeuchi |
| 2nd Author's Affiliation | Waseda University(Waseda Univ.) |
| 3rd Author's Name | Jiro Katto |
| 3rd Author's Affiliation | Waseda University(Waseda Univ.) |
| Date | 2017-03-06 |
| Paper # | IMQ2016-26,IE2016-141,MVE2016-49 |
| Volume (vol) | vol.116 |
| Number (no) | IMQ-494,IE-495,MVE-496 |
| Page | pp.pp.37-42(IMQ), pp.37-42(IE), pp.37-42(MVE), |
| #Pages | 6 |
| Date of Issue | 2017-02-27 (IMQ, IE, MVE) |