Presentation 2020-03-16
Image compression by colorization
Hiya Roy, Subhajit Chaudhury, Toshihiko Yamasaki, Tatsuaki Hashimoto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Image compression techniques exploit the inherent psycho-visual limitations in human vision to reduce the number of bits required to store an image without degrading its perceptual quality. ?While most recent methods use an encoder-decoder based Convolutional Neural Networks (CNN) features, our approach focuses on limiting the size of the compressed representation by sampling and storing some color informative pixels of the chrominance channels. We propose a uniform sampler-based encoder, that chooses and stores only a few color informative pixels. During decoding, we use these color values from a few selected pixels along with the luminance channel to reconstruct the full-color image that looks perceptually similar to the original image. Experimental results prove the effectiveness of the proposed method by demonstrating comparable or better performance compared to the state-of-the-art methods in image compression.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Lossy image compressionColorizationDeep neural networks
Paper # PRMU2019-86
Date of Issue 2020-03-09 (PRMU)

Conference Information
Committee PRMU / IPSJ-CVIM
Conference Date 2020/3/16(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Yoichi Sato(Univ. of Tokyo)
Vice Chair Toru Tamaki(Hiroshima Univ.) / Akisato Kimura(NTT)
Secretary Toru Tamaki(NTT) / Akisato Kimura(OMRON SINICX)
Assistant Yusuke Uchida(DeNA) / Takayoshi Yamashita(Chubu Univ.)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding / Special Interest Group on Computer Vision and Image Media
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Image compression by colorization
Sub Title (in English)
Keyword(1) Lossy image compressionColorizationDeep neural networks
1st Author's Name Hiya Roy
1st Author's Affiliation The University of Tokyo(UTokyo)
2nd Author's Name Subhajit Chaudhury
2nd Author's Affiliation The University of Tokyo(UTokyo)
3rd Author's Name Toshihiko Yamasaki
3rd Author's Affiliation The University of Tokyo(UTokyo)
4th Author's Name Tatsuaki Hashimoto
4th Author's Affiliation The University of Tokyo(UTokyo)
Date 2020-03-16
Paper # PRMU2019-86
Volume (vol) vol.119
Number (no) PRMU-481
Page pp.pp.107-108(PRMU),
#Pages 2
Date of Issue 2020-03-09 (PRMU)