| Presentation | 2022-06-09 Learning Method for Image Denoising by Weighted Sum of Perceptual Quality Assessment Methods Takamichi Miyata, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Existing deep learning-based denoising methods employ mean squared error (MSE) as a loss function. As a result, the output image is excessively smoothed and has low perceptual quality. On the other hand, image quality assessment (IQA), which uses deep learning to estimate the perceptual quality of images, has been proposed. However, existing studies have reported that when such IQA is used alone as a loss function in denoising methods, not only is the signal quality significantly degraded, but also the perceptual quality is not improved. This is most likely due to the presence of certain images in each IQA that cause the IQA in question to malfunction. To avoid the aforementioned problem and improve the perceptual quality of denoised images, we propose a method for learning denoising methods using a loss function that combines IQA with other IQA or MSE. To confirm the effectiveness of the proposed method, we qualitatively and quantitatively compared the denoising performance of the proposed method with that of comparative methods. The results show that the proposed method reduces excessive smoothing of the image and improves the perceived quality by strongly adding texture. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Image denoising / deep learning / perceptual quality |
| Paper # | NLP2022-2,CCS2022-2 |
| Date of Issue | 2022-06-02 (NLP, CCS) |
| Conference Information | |
| Committee | CCS / NLP |
|---|---|
| Conference Date | 2022/6/9(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Megumi Akai(Hokkaido Univ.) / Akio Tsuneda(Kumamoto Univ.) |
| Vice Chair | Masaki Aida(TMU) / Hidehiro Nakano(Tokyo City Univ.) / Hiroyuki Torikai(Hosei Univ.) |
| Secretary | Masaki Aida(TDK) / Hidehiro Nakano(Shibaura Insti. of Tech.) / Hiroyuki Torikai(Sojo Univ.) |
| Assistant | Tomoyuki Sasaki(Shonan Instit. of Tech.) / Hiroyasu Ando(Tsukuba Univ.) / Miki Kobayashi(Rissho Univ.) / " Hiroyuki YASUDA(The Univ. of Tokyo) / Yuichi Yokoi(Nagasaki Univ.) / Yoshikazu Yamanaka(Utsunomiya Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Complex Communication Sciences / Technical Committee on Nonlinear Problems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Learning Method for Image Denoising by Weighted Sum of Perceptual Quality Assessment Methods |
| Sub Title (in English) | |
| Keyword(1) | Image denoising |
| Keyword(2) | deep learning |
| Keyword(3) | perceptual quality |
| 1st Author's Name | Takamichi Miyata |
| 1st Author's Affiliation | Chiba Institute of Technology(Chiba Inst. Tech.) |
| Date | 2022-06-09 |
| Paper # | NLP2022-2,CCS2022-2 |
| Volume (vol) | vol.122 |
| Number (no) | NLP-65,CCS-66 |
| Page | pp.pp.7-12(NLP), pp.7-12(CCS), |
| #Pages | 6 |
| Date of Issue | 2022-06-02 (NLP, CCS) |