Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2311.09178 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909447262044160 |
|---|---|
| author | Sulaiman, Marwah Shehabeldin, Zahraa Fahmy, Israa Barakat, Mohammed El-Naggar, Mohammed Hussein, Dareen Youssef, Moustafa Eraqi, Hesham M. |
| author_facet | Sulaiman, Marwah Shehabeldin, Zahraa Fahmy, Israa Barakat, Mohammed El-Naggar, Mohammed Hussein, Dareen Youssef, Moustafa Eraqi, Hesham M. |
| contents | Recently, video super resolution (VSR) has become a very impactful task in the area of Computer Vision due to its various applications. In this paper, we propose Recurrent Back-Projection Generative Adversarial Network (RBPGAN) for VSR in an attempt to generate temporally coherent solutions while preserving spatial details. RBPGAN integrates two state-of-the-art models to get the best in both worlds without compromising the accuracy of produced video. The generator of the model is inspired by RBPN system, while the discriminator is inspired by TecoGAN. We also utilize Ping-Pong loss to increase temporal consistency over time. Our contribution together results in a model that outperforms earlier work in terms of temporally consistent details, as we will demonstrate qualitatively and quantitatively using different datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_09178 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | RBPGAN: Recurrent Back-Projection GAN for Video Super Resolution Sulaiman, Marwah Shehabeldin, Zahraa Fahmy, Israa Barakat, Mohammed El-Naggar, Mohammed Hussein, Dareen Youssef, Moustafa Eraqi, Hesham M. Computer Vision and Pattern Recognition Recently, video super resolution (VSR) has become a very impactful task in the area of Computer Vision due to its various applications. In this paper, we propose Recurrent Back-Projection Generative Adversarial Network (RBPGAN) for VSR in an attempt to generate temporally coherent solutions while preserving spatial details. RBPGAN integrates two state-of-the-art models to get the best in both worlds without compromising the accuracy of produced video. The generator of the model is inspired by RBPN system, while the discriminator is inspired by TecoGAN. We also utilize Ping-Pong loss to increase temporal consistency over time. Our contribution together results in a model that outperforms earlier work in terms of temporally consistent details, as we will demonstrate qualitatively and quantitatively using different datasets. |
| title | RBPGAN: Recurrent Back-Projection GAN for Video Super Resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2311.09178 |