| Presentation | 2023-03-03 [Tutorial Lecture] On Semantic Image Processing with Autoencoder Hiroyuki Tsuji, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Variational Auto Encoder (VAE) has a conceptually well-structured latent space and can realize semantic image manipulation through simple vector operations on the latent space, but on the other hand, it is known to have image quality problems such as blurring in the reconstructed image. Recently, autoencoders that employ generators of deep generative models such as GAN and diffusion models as decoders, combined with encoders that map arbitrary inputs to the latent space, have been proposed to enable high-quality image reconstruction that could not be achieved with VAE.This paper describes the recent trends of Encoder-Generator type autoencoders and semantic image processing using these autoencoders. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Deep generative model / Autoencoder / VAE / GAN / Duffusion model / Latent space |
| Paper # | SIS2022-58 |
| Date of Issue | 2023-02-23 (SIS) |
| Conference Information | |
| Committee | SIS |
|---|---|
| Conference Date | 2023/3/2(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Chiba Institute of Technology |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Tomoaki Kimura(Kanagawa Inst. of Tech.) |
| Vice Chair | Naoto Sasaoka(Tottori Univ.) / Hakaru Tamukoh(Kyushu Inst. of Tech.) |
| Secretary | Naoto Sasaoka(NTT) / Hakaru Tamukoh(Kansai Univ.) |
| Assistant | Yoshiaki Makabe(Kanagawa Inst. of Tech.) / Yosuke Sugiura(Saitama Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Smart Info-Media Systems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | [Tutorial Lecture] On Semantic Image Processing with Autoencoder |
| Sub Title (in English) | |
| Keyword(1) | Deep generative model |
| Keyword(2) | Autoencoder |
| Keyword(3) | VAE |
| Keyword(4) | GAN |
| Keyword(5) | Duffusion model |
| Keyword(6) | Latent space |
| 1st Author's Name | Hiroyuki Tsuji |
| 1st Author's Affiliation | Kanagawa Institute of Technology(KAIT) |
| Date | 2023-03-03 |
| Paper # | SIS2022-58 |
| Volume (vol) | vol.122 |
| Number (no) | SIS-410 |
| Page | pp.pp.97-102(SIS), |
| #Pages | 6 |
| Date of Issue | 2023-02-23 (SIS) |