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 I2SB 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.
@article{arxiv.2504.13622,
title = {SupResDiffGAN a new approach for the Super-Resolution task},
author = {Dawid Kopeć and Wojciech Kozłowski and Maciej Wizerkaniuk and Dawid Krutul and Jan Kocoń and Maciej Zięba},
journal= {arXiv preprint arXiv:2504.13622},
year = {2025}
}
Comments
25th International Conference on Computational Science