| Presentation | 2021-03-01 VVC Video Coding with Deep Learning Based Frame Interpolation Joi Shimizu, Heming Sun, Jiro Katto, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Recently, many deep learning based models for frame interpolation have been proposed. In this paper, we propose a novel video compression method which incorporates deep learning based frame interpolation into VVC which is the newest current video compression standard. First, by using VVC Random Access mode, the even frames in the video are compressed (when video frames are counted from 0). During decoding, from the decoded even frames, the odd frames are generated using frame interpolation. We also consider encoding of the residuals between the predicted odd frames and the actual frames. Experimental results show that our approach can perform similar to VVC in some scenarios. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Video Compression / Interpolation / Deep Learning |
| Paper # | IMQ2020-18,IE2020-58,MVE2020-50 |
| Date of Issue | 2021-02-22 (IMQ, IE, MVE) |
| Conference Information | |
| Committee | MVE / IMQ / IE / CQ |
|---|---|
| Conference Date | 2021/3/1(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Masayuki Ihara(NTT) / Toshiya Nakaguchi(Chiba Univ.) / Hideaki Kimata(NTT) / Hideyuki Shimonishi(NEC) |
| Vice Chair | Kiyoshi Kiyokawa(NAIST) / Mitsuru Maeda(Canon) / Kenya Uomori(Osaka Univ.) / Kazuya Kodama(NII) / Keita Takahashi(Nagoya Univ.) / Jun Okamoto(NTT) / Takefumi Hiraguri(Nippon Inst. of Tech.) |
| Secretary | Kiyoshi Kiyokawa(Oosaka Inst. of Tech.) / Mitsuru Maeda(NTT) / Kenya Uomori(Univ. of ToKyo) / Kazuya Kodama(Shizuoka Univ.) / Keita Takahashi(Sony Semiconductor Solutions) / Jun Okamoto(KDDI Research) / Takefumi Hiraguri(Nagoya Inst. of Tech.) |
| Assistant | Naoya Isoyama(NAIST) / Takenori Hara(DNP) / Mitsuhiro Goto(NTT) / Hiroaki Kudo(Nagoya Univ.) / Masaru Tsuchida(NTT) / Keita Hirai(Chiba Univ.) / Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT) / Yoshiaki Nishikawa(NEC) / Takuto Kimura(NTT) / Ryoichi Kataoka(KDDI Research) |
| Paper Information | |
| Registration To | Technical Committee on Media Experience and Virtual Environment / Technical Committee on Image Media Quality / Technical Committee on Image Engineering / Technical Committee on Communication Quality |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | VVC Video Coding with Deep Learning Based Frame Interpolation |
| Sub Title (in English) | |
| Keyword(1) | Video Compression |
| Keyword(2) | Interpolation |
| Keyword(3) | Deep Learning |
| 1st Author's Name | Joi Shimizu |
| 1st Author's Affiliation | Waseda University(Waseda Univ.) |
| 2nd Author's Name | Heming Sun |
| 2nd Author's Affiliation | Waseda University(Waseda Univ.) |
| 3rd Author's Name | Jiro Katto |
| 3rd Author's Affiliation | Waseda University(Waseda Univ.) |
| Date | 2021-03-01 |
| Paper # | IMQ2020-18,IE2020-58,MVE2020-50 |
| Volume (vol) | vol.120 |
| Number (no) | IMQ-389,IE-390,MVE-391 |
| Page | pp.pp.40-45(IMQ), pp.40-45(IE), pp.40-45(MVE), |
| #Pages | 6 |
| Date of Issue | 2021-02-22 (IMQ, IE, MVE) |