Presentation 2021-06-03
A Study on Compression Artifacts Reduction by a Super-Resolution Network
Shion Komatsu, Joi Shimizu, Heming Sun, Jiro Katto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Due to the huge amount of information in digital video signals, video compression is used to reduce the amount of information during storage and transmission. In particular, lossy compression can greatly reduce the amount of information. However, irreversible processing cannot completely restore the input images, and compression artifacts, such as block noise and mosquito noise, are generated. The compression process is designed to make the noise visually unnoticeable, but as the compression ratio increases, the coding distortion becomes more noticeable. In this paper, we propose a method to reduce the coding distortion by applying a super-resolution network as a post-filter to videos encoded by existing video compression techniques such as HEVC. The effectiveness and characteristics of the proposed method are discussed through experiments.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Compression Artifacts / Super Resolution / Video Compression / Deep Learning
Paper # SIP2021-4,BioX2021-4,IE2021-4
Date of Issue 2021-05-27 (SIP, BioX, IE)

Conference Information
Committee IE / SIP / BioX / ITE-IST / ITE-ME
Conference Date 2021/6/3(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Hideaki Kimata(Kogakuin Univ.) / Kazunori Hayashi(Kyoto Univ.) / Akira Otsuka(AIST) / Junichi Akita(Kanazawa Univ.) / Hiroyuki Arai(Nippon Inst. of Tech.)
Vice Chair Kazuya Kodama(NII) / Keita Takahashi(Nagoya Univ.) / Yukihiro Bandou(NTT) / Toshihisa Tanaka(Tokyo Univ. Agri.&Tech.) / Takahiro Aoki(Fujitsu Labs.) / Masatsugu Ichino(Univ. of Electro-Comm.) / Yutaka Hirose(Panasonic)
Secretary Kazuya Kodama(KDDI Research) / Keita Takahashi(Nagoya Inst. of Tech.) / Yukihiro Bandou(Hosei Univ.) / Toshihisa Tanaka(Waseda Univ.) / Takahiro Aoki(SECOM) / Masatsugu Ichino(KDDI Research) / Yutaka Hirose(Saitama Univ.)
Assistant Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT) / Yuichi Tanaka(Tokyo Univ. Agri.&Tech.) / Emiko Sano(MitsubishiElectric) / Akihiro Hayasaka(NEC)

Paper Information
Registration To Technical Committee on Image Engineering / Technical Committee on Signal Processing / Technical Committee on Biometrics / Technical Group on Information Sensing Technologies / Technical Group on Media Engineering
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study on Compression Artifacts Reduction by a Super-Resolution Network
Sub Title (in English)
Keyword(1) Compression Artifacts
Keyword(2) Super Resolution
Keyword(3) Video Compression
Keyword(4) Deep Learning
1st Author's Name Shion Komatsu
1st Author's Affiliation Waseda University(Waseda Univ.)
2nd Author's Name Joi Shimizu
2nd Author's Affiliation Waseda University(Waseda Univ.)
3rd Author's Name Heming Sun
3rd Author's Affiliation Waseda University(Waseda Univ.)
4th Author's Name Jiro Katto
4th Author's Affiliation Waseda University(Waseda Univ.)
Date 2021-06-03
Paper # SIP2021-4,BioX2021-4,IE2021-4
Volume (vol) vol.121
Number (no) SIP-54,BioX-55,IE-56
Page pp.pp.15-20(SIP), pp.15-20(BioX), pp.15-20(IE),
#Pages 6
Date of Issue 2021-05-27 (SIP, BioX, IE)