Presentation | 2021-11-25 wganBCS: Block-wise image compressive sensing and reconstruction model using adversarial training to eliminate block effects Boyan Chen, Kaoru Uchida, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The famous block-wise compressive sensing (BCS) paradigm can greatly reduce the memory consumption of sensingmatrix compared with traditional image compressive methods. However, BCS paradigm still suffers from two issues. One is thatblock-wise sensing causes heavy block effect on the reconstructed image, which leads to degradation in the image quality metrics. Another is that the sate of art block wise image compressive sensing methods only use mean square error loss function to optimizetheir models, which causes the reconstructed images over smoothed. In this paper, we incorporate generative adversarial traininginto BCS paradigm and propose a new block wise image compressive sensing and reconstruction model called wganBCS, which acombination of traditional L2 loss and the wasserstein loss are used to optimize the model. We propose a modified wasserstein GAN(WGAN) network to deal with the block effect caused by the block wise compressive sensing. Specifically speaking, the generatornetwork will minimize the wasserstein distance calculated by the critic network to keep the reconstructed images visually authenticto ground truth images. Experimental result shows that our model is superior both in visual authenticity and the image qualitymetrics compared to most state of art image compressive sensing methods. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Image compressed sensingGenerative adversarial NetworksDeep Learning |
Paper # | CS2021-60,IE2021-19 |
Date of Issue | 2021-11-18 (CS, IE) |
Conference Information | |
Committee | IPSJ-AVM / CS / IE / ITE-BCT |
---|---|
Conference Date | 2021/11/25(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Image coding, Communications and streaming technologies, etc. |
Chair | 笠井 裕之(早大) / Jun Terada(NTT) / Kazuya Kodama(NII) / Kyoichi Saito(NHK) |
Vice Chair | / Daisuke Umehara(Kyoto Inst. of Tech.) / Hiroyuki Bandoh(NTT) / Toshihiko Yamazaki(Univ. of Tokyo) / Hidekazu Murata(Kyoto Univ.) / Hajime Saito(TV Tokyo) |
Secretary | (早大) / Daisuke Umehara(KDDI) / Hiroyuki Bandoh(NTT) / Toshihiko Yamazaki(NICT) / Hidekazu Murata(NTT) / Hajime Saito(KDDI Research) |
Assistant | / Takahiro Yamaura(Toshiba) / Yuta Ida(Yamaguchi Univ.) / Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT) / Tatsuhiko Itokawa(Mitsubishi Electric) / Takumi Matsumoto(Furukawa Electric) / Takeshi Maruyama(Furukawa Electric) / Yoshie Enoki(TBS) |
Paper Information | |
Registration To | The Special Interest Groups of Audio Visual and Multimedia Information Processing / Technical Committee on Communication Systems / Technical Committee on Image Engineering / Technical Group on Broadcasting and Communication Technologies |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | wganBCS: Block-wise image compressive sensing and reconstruction model using adversarial training to eliminate block effects |
Sub Title (in English) | |
Keyword(1) | Image compressed sensingGenerative adversarial NetworksDeep Learning |
1st Author's Name | Boyan Chen |
1st Author's Affiliation | Hosei University/Northwestern Polytechnical University(Hosei Univ./NPU) |
2nd Author's Name | Kaoru Uchida |
2nd Author's Affiliation | Hosei University(Hosei Univ.) |
Date | 2021-11-25 |
Paper # | CS2021-60,IE2021-19 |
Volume (vol) | vol.121 |
Number (no) | CS-268,IE-269 |
Page | pp.pp.1-6(CS), pp.1-6(IE), |
#Pages | 6 |
Date of Issue | 2021-11-18 (CS, IE) |