融合GAN与扩散模型，实现快速高质超分辨率重建。
SupResDiffGAN a new approach for the Super-Resolution task
- 结合GAN与扩散模型的混合架构，利用潜空间加速推理。
- 推理速度远超SR3、I²SB等扩散模型，保持优秀视觉质量。
- 提出自适应噪声扰动防判别器过拟合，适合实时高清图像生成应用。
本文提出SupResDiffGAN，一种融合生成对抗网络（GAN）与扩散模型优势的新型混合架构，用于超分辨率任务。通过利用潜空间表示并减少扩散步数，该方法在保持优异感知质量的同时，显著提升了推理速度，优于传统扩散模型如SR3和I²SB。为防止判别器过拟合，我们提出自适应噪声扰动机制，确保训练过程中生成器与判别器的稳定平衡。在多个基准数据集上的大量实验表明，该方法有效缩小了扩散模型与GAN类方法之间的性能差距，为高分辨率图像生成的实时应用奠定基础。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。