| Presentation | 2019-06-13 Single Image Super-Resolution for being flexible to downsampling kernel by using self-examplers Shogo Seta, Takuro Yamaguchi, Masaaki Ikehara, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We propose a fast single super resolution which is comparable image quality with conventional methods without being based on external exemplars.Conventional methods reconstruct high-resolution images from low resolution images by learning mapping to the HR space. Because of external exemplarｓ,the method reconstructs a high quality image ,but it takes a long time to learn and costs large memory.This is not preferred for real applications.To improve it ,Proposed method learns mapping by using self exemlars.In this report,we propose a single super resolution with self learning and based on optimization with l2 norm constraint to achieve a fast and small memory method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | a single super resolution / self learning / sparse cording, / L2 norm / self dictionary / self simirality |
| Paper # | SIS2019-6 |
| Date of Issue | 2019-06-06 (SIS) |
| Conference Information | |
| Committee | SIS / IPSJ-AVM / ITE-3DIT |
|---|---|
| Conference Date | 2019/6/13(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Fukue Culture Center |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Intelligent Multimedia Systems, Applied Enbedded Systems, Three-Dimensional Image Technology (3DIT), etc. |
| Chair | Takayuki Nakachi(NTT) / Sei Naito(KDDI Research, Inc.) / Tsutomu Horikoshi(Shonan Institute of Technology) |
| Vice Chair | Noriaki Suetake(Yamaguchi Univ.) / Tomoaki Kimura(Kanagawa Inst. of Tech.) |
| Secretary | Noriaki Suetake(Tokyo Metropolitan Univ.) / Tomoaki Kimura(Kindai Univ.) / (NTT) / (Tokyo Univ. of Science) |
| Assistant | Hideaki Misawa(National Inst. of Tech., Ube College) / Yukihiro Bandoh(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Smart Info-Media Systems / Special Interest Group on Audio Visual and Multimedia Information Processing / Technical Group on Three-Dimensional Image Technology |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Single Image Super-Resolution for being flexible to downsampling kernel by using self-examplers |
| Sub Title (in English) | |
| Keyword(1) | a single super resolution |
| Keyword(2) | self learning |
| Keyword(3) | sparse cording, |
| Keyword(4) | L2 norm |
| Keyword(5) | self dictionary |
| Keyword(6) | self simirality |
| 1st Author's Name | Shogo Seta |
| 1st Author's Affiliation | Keio University(Keio Univ) |
| 2nd Author's Name | Takuro Yamaguchi |
| 2nd Author's Affiliation | Keio University(Keio Univ) |
| 3rd Author's Name | Masaaki Ikehara |
| 3rd Author's Affiliation | Keio University(Keio Univ) |
| Date | 2019-06-13 |
| Paper # | SIS2019-6 |
| Volume (vol) | vol.119 |
| Number (no) | SIS-78 |
| Page | pp.pp.29-34(SIS), |
| #Pages | 6 |
| Date of Issue | 2019-06-06 (SIS) |