SupResDiffGAN a new approach for the Super-Resolution task
This work addresses the efficiency bottleneck in diffusion-based super-resolution for real-time high-resolution image generation applications, representing an incremental but practical advance.
The authors tackled the problem of slow inference in diffusion-based super-resolution models by proposing SupResDiffGAN, a hybrid GAN-diffusion architecture that reduces diffusion steps and uses adaptive noise corruption to prevent discriminator overfitting. The result is significantly faster inference times while maintaining competitive perceptual quality, outperforming models like SR3 and I²SB in efficiency and image quality.
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.