GAN-Diff : Coupling Pretrained WGAN-GP Features with Conditional Diffusion U-Nets

2026-08-23

AI Summary

该研究通过结合预训练的WGAN-GP特征与条件扩散U-Net，解决了图像恢复中的质量和效率问题，提高了去噪和超分辨率性能。

Abstract

Generative adversarial networks (GANs) can provide efficient image generation, while diffusion models offer high-quality image restoration but require iterative sampling. This paper presents a hybrid GAN-guided diffusion framework that uses a pretrained Wasserstein GAN with gradient penalty (WGAN-GP) as a feature prior for conditional diffusion-based image restoration. Intermediate features from the frozen WGAN-GP generator are incorporated into a diffusion U-Net through cross-attention and remain fixed during the DDIM sampling process. The framework is evaluated on two restoration tasks, Gaussian denoising and 2Xsuper-resolution, using CelebA face images. During development, several sources of instability were identified and addressed, including adversarial learning-rate imbalance, inappropriate diffusion initialization, excessive corruption, and insufficient parameter averaging. The resulting framework consistently improves the quality of both degraded and low-resolution images. In particular, it improves denoising performance by 4.40 dB in PSNR and super-resolution performance by 3.70 dB over their respective input baselines. These results demonstrate the potential of a frozen GAN feature prior to guide diffusion models toward stable and effective image restoration.

Problem

• GAN
• diffusion models
• image restoration
• WGAN-GP
• conditional diffusion

Innovation

• GAN-guided diffusion
• WGAN-GP feature prior
• conditional diffusion U-Net
• cross-attention
• image restoration