| Paper Abstract and Keywords |
| Presentation |
2025-11-30 11:30
High-Resolution Image Generation using Deep Learning-based Super-Resolution
Shin Nomiyama, Yinhao Li (Ritsumeikan Univ.), Kento Kozono, Miwa Gotou (TOKYO KEIKI), Yen-Wei Chen (Ritsumeikan Univ.) |
| Abstract |
(in Japanese) |
(See Japanese page) |
| (in English) |
Conventional super-resolution (SR) methods, which prioritize mathematical metrics like the Peak Signal-to-Noise Ratio (PSNR), achieve high fidelity to the source image. However, they often lack perceptual quality, leading to issues such as blurriness and text artifacts. This problem is especially critical for film images like food packaging and labels, where text must be magnified with both accuracy and clarity. The inherent trade-off between fidelity and perceptual quality has been a significant barrier in this context.
In this research, we design a model using a composite loss function that emphasizes perceptual quality. By integrating this model with a traditional PSNR-oriented model via Network Interpolation, our proposed method resolves this trade-off, generating SR images that are both faithful to the original and perceptually sharp. |
| Keyword |
(in Japanese) |
(See Japanese page) |
| (in English) |
Super-Resolution / GAN / Loss Function / Perceptual Quality / / / / |
| Reference Info. |
ITE Tech. Rep. |
| Paper # |
|
| Date of Issue |
|
| ISSN |
|
| Download PDF |
|
| Conference Information |
| Committee |
KANSAI |
| Conference Date |
2025-11-30 - 2025-11-30 |
| Place (in Japanese) |
(See Japanese page) |
| Place (in English) |
OMU I-site Namba |
| Topics (in Japanese) |
(See Japanese page) |
| Topics (in English) |
The Institute of Image Information and Television Engineers, Kansai chapter, Workshop for young researchers |
| Paper Information |
| Registration To |
KANSAI |
| Conference Code |
2025-11-KANSAI |
| Language |
Japanese |
| Title (in Japanese) |
(See Japanese page) |
| Sub Title (in Japanese) |
(See Japanese page) |
| Title (in English) |
High-Resolution Image Generation using Deep Learning-based Super-Resolution |
| Sub Title (in English) |
|
| Keyword(1) |
Super-Resolution |
| Keyword(2) |
GAN |
| Keyword(3) |
Loss Function |
| Keyword(4) |
Perceptual Quality |
| Keyword(5) |
|
| Keyword(6) |
|
| Keyword(7) |
|
| Keyword(8) |
|
| 1st Author's Name |
Shin Nomiyama |
| 1st Author's Affiliation |
Ritsumeikan University (Ritsumeikan Univ.) |
| 2nd Author's Name |
Yinhao Li |
| 2nd Author's Affiliation |
Ritsumeikan University (Ritsumeikan Univ.) |
| 3rd Author's Name |
Kento Kozono |
| 3rd Author's Affiliation |
TOKYO KEIKI INC. (TOKYO KEIKI) |
| 4th Author's Name |
Miwa Gotou |
| 4th Author's Affiliation |
TOKYO KEIKI INC. (TOKYO KEIKI) |
| 5th Author's Name |
Yen-Wei Chen |
| 5th Author's Affiliation |
Ritsumeikan University (Ritsumeikan Univ.) |
| 6th Author's Name |
|
| 6th Author's Affiliation |
() |
| 7th Author's Name |
|
| 7th Author's Affiliation |
() |
| 8th Author's Name |
|
| 8th Author's Affiliation |
() |
| 9th Author's Name |
|
| 9th Author's Affiliation |
() |
| 10th Author's Name |
|
| 10th Author's Affiliation |
() |
| 11th Author's Name |
|
| 11th Author's Affiliation |
() |
| 12th Author's Name |
|
| 12th Author's Affiliation |
() |
| 13th Author's Name |
|
| 13th Author's Affiliation |
() |
| 14th Author's Name |
|
| 14th Author's Affiliation |
() |
| 15th Author's Name |
|
| 15th Author's Affiliation |
() |
| 16th Author's Name |
|
| 16th Author's Affiliation |
() |
| 17th Author's Name |
|
| 17th Author's Affiliation |
() |
| 18th Author's Name |
|
| 18th Author's Affiliation |
() |
| 19th Author's Name |
|
| 19th Author's Affiliation |
() |
| 20th Author's Name |
|
| 20th Author's Affiliation |
() |
| 21st Author's Name |
|
| 21st Author's Affiliation |
() |
| 22nd Author's Name |
|
| 22nd Author's Affiliation |
() |
| 23rd Author's Name |
|
| 23rd Author's Affiliation |
() |
| 24th Author's Name |
|
| 24th Author's Affiliation |
() |
| 25th Author's Name |
|
| 25th Author's Affiliation |
() |
| 26th Author's Name |
/ / |
| 26th Author's Affiliation |
()
() |
| 27th Author's Name |
/ / |
| 27th Author's Affiliation |
()
() |
| 28th Author's Name |
/ / |
| 28th Author's Affiliation |
()
() |
| 29th Author's Name |
/ / |
| 29th Author's Affiliation |
()
() |
| 30th Author's Name |
/ / |
| 30th Author's Affiliation |
()
() |
| 31st Author's Name |
/ / |
| 31st Author's Affiliation |
()
() |
| 32nd Author's Name |
/ / |
| 32nd Author's Affiliation |
()
() |
| 33rd Author's Name |
/ / |
| 33rd Author's Affiliation |
()
() |
| 34th Author's Name |
/ / |
| 34th Author's Affiliation |
()
() |
| 35th Author's Name |
/ / |
| 35th Author's Affiliation |
()
() |
| 36th Author's Name |
/ / |
| 36th Author's Affiliation |
()
() |
| Speaker |
Author-1 |
| Date Time |
2025-11-30 11:30:00 |
| Presentation Time |
15 minutes |
| Registration for |
KANSAI |
| Paper # |
|
| Volume (vol) |
vol. |
| Number (no) |
|
| Page |
|
| #Pages |
|
| Date of Issue |
|