SupResDiffGAN a new approach for the Super-Resolution task
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915249971527680 |
|---|---|
| author | Kopeć, Dawid Kozłowski, Wojciech Wizerkaniuk, Maciej Krutul, Dawid Kocoń, Jan Zięba, Maciej |
| author_facet | Kopeć, Dawid Kozłowski, Wojciech Wizerkaniuk, Maciej Krutul, Dawid Kocoń, Jan Zięba, Maciej |
| contents | In this work, we present SupResDiffGAN, a novel hybrid architecture that combines the strengths of Generative Adversarial Networks (GANs) and diffusion models for super-resolution tasks. By leveraging latent space representations and reducing the number of diffusion steps, SupResDiffGAN achieves significantly faster inference times than other diffusion-based super-resolution models while maintaining competitive perceptual quality. To prevent discriminator overfitting, we propose adaptive noise corruption, ensuring a stable balance between the generator and the discriminator during training. Extensive experiments on benchmark datasets show that our approach outperforms traditional diffusion models such as SR3 and I$^2$SB in efficiency and image quality. This work bridges the performance gap between diffusion- and GAN-based methods, laying the foundation for real-time applications of diffusion models in high-resolution image generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_13622 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SupResDiffGAN a new approach for the Super-Resolution task Kopeć, Dawid Kozłowski, Wojciech Wizerkaniuk, Maciej Krutul, Dawid Kocoń, Jan Zięba, Maciej Image and Video Processing Computer Vision and Pattern Recognition In this work, we present SupResDiffGAN, a novel hybrid architecture that combines the strengths of Generative Adversarial Networks (GANs) and diffusion models for super-resolution tasks. By leveraging latent space representations and reducing the number of diffusion steps, SupResDiffGAN achieves significantly faster inference times than other diffusion-based super-resolution models while maintaining competitive perceptual quality. To prevent discriminator overfitting, we propose adaptive noise corruption, ensuring a stable balance between the generator and the discriminator during training. Extensive experiments on benchmark datasets show that our approach outperforms traditional diffusion models such as SR3 and I$^2$SB in efficiency and image quality. This work bridges the performance gap between diffusion- and GAN-based methods, laying the foundation for real-time applications of diffusion models in high-resolution image generation. |
| title | SupResDiffGAN a new approach for the Super-Resolution task |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.13622 |