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

• URL: http://arxiv.org/abs/2608.22272v2
• Date: Thu, 27 Aug 2026 23:25:43 GMT
• Title: GAN-Diff : Coupling Pretrained WGAN-GP Features with Conditional Diffusion U-Nets
• Abstract summary: This paper presents a hybrid GAN-guided diffusion framework that uses a pretrained Wasserstein GAN with gradient penalty (WGAN-GP)<n> Intermediate features from the frozen WGAN-GP generator are incorporated into a diffusion U-Net through cross-attention.<n>The framework consistently improves the quality of both degraded and low-resolution images.
• Score: 0.14053129774629072
• License: http://creativecommons.org/publicdomain/zero/1.0/
• 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.

Related papers

• Diffusion Once and Done: Degradation-Aware LoRA for Efficient All-in-One Image Restoration [14.922600858354983]
  Diffusion Once and Done (DOD) method aims to achieve superior restoration performance with only one-step sampling of Stable Diffusion (SD) models.<n>Our method outperforms existing diffusion-based restoration approaches in both visual quality and inference efficiency.
  arXiv  Detail & Related papers  (2025-08-05T12:26:28Z)
• SING: Semantic Image Communications using Null-Space and INN-Guided Diffusion Models [52.40011613324083]
  Joint source-channel coding systems (DeepJSCC) have recently demonstrated remarkable performance in wireless image transmission.<n>Existing methods focus on minimizing distortion between the transmitted image and the reconstructed version at the receiver, often overlooking perceptual quality.<n>We propose SING, a novel framework that formulates the recovery of high-quality images from corrupted reconstructions as an inverse problem.
  arXiv  Detail & Related papers  (2025-03-16T12:32:11Z)
• A Wavelet Diffusion GAN for Image Super-Resolution [7.986370916847687]
  Diffusion models have emerged as a superior alternative to generative adversarial networks (GANs) for high-fidelity image generation.<n>However, their real-time feasibility is hindered by slow training and inference speeds.<n>This study proposes a wavelet-based conditional Diffusion GAN scheme for Single-Image Super-Resolution.
  arXiv  Detail & Related papers  (2024-10-23T15:34:06Z)
• RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusion [29.277211609920155]
  We present Relay Residual Diffusion Extreme Image Compression (RDEIC)<n>We first use the compressed latent features of the image with added noise, instead of pure noise, as the starting point to eliminate the unnecessary initial stages of the denoising process.<n>RDEIC achieves state-of-the-art visual quality and outperforms existing diffusion-based extreme image compression methods in both fidelity and efficiency.
  arXiv  Detail & Related papers  (2024-10-03T16:24:20Z)
• Latent Denoising Diffusion GAN: Faster sampling, Higher image quality [0.0]
  Latent Denoising Diffusion GAN employs pre-trained autoencoders to compress images into a compact latent space. Compared to its predecessors, DiffusionGAN and Wavelet Diffusion, our model shows remarkable improvements in all evaluation metrics.
  arXiv  Detail & Related papers  (2024-06-17T16:32:23Z)
• HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models [38.74983301496911]
  Hyperspectral image (HSI) restoration aims at recovering clean images from degraded observations. Existing model-based methods have limitations in accurately modeling the complex image characteristics. This paper proposes an unsupervised HSI restoration framework with pre-trained diffusion model (HIR-Diff)
  arXiv  Detail & Related papers  (2024-02-24T17:15:05Z)
• Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model [59.08821399652483]
  Illumination degradation image restoration (IDIR) techniques aim to improve the visibility of degraded images and mitigate the adverse effects of deteriorated illumination. Among these algorithms, diffusion model (DM)-based methods have shown promising performance but are often burdened by heavy computational demands and pixel misalignment issues when predicting the image-level distribution. We propose to leverage DM within a compact latent space to generate concise guidance priors and introduce a novel solution called Reti-Diff for the IDIR task. Reti-Diff comprises two key components: the Retinex-based latent DM (RLDM) and the Retinex-guided transformer (RG
  arXiv  Detail & Related papers  (2023-11-20T09:55:06Z)
• Deep Equilibrium Diffusion Restoration with Parallel Sampling [120.15039525209106]
  Diffusion model-based image restoration (IR) aims to use diffusion models to recover high-quality (HQ) images from degraded images, achieving promising performance. Most existing methods need long serial sampling chains to restore HQ images step-by-step, resulting in expensive sampling time and high computation costs. In this work, we aim to rethink the diffusion model-based IR models through a different perspective, i.e., a deep equilibrium (DEQ) fixed point system, called DeqIR.
  arXiv  Detail & Related papers  (2023-11-20T08:27:56Z)
• Learning A Coarse-to-Fine Diffusion Transformer for Image Restoration [39.071637725773314]
  We propose a coarse-to-fine diffusion Transformer (C2F-DFT) for image restoration. C2F-DFT contains diffusion self-attention (DFSA) and diffusion feed-forward network (DFN) In the coarse training stage, our C2F-DFT estimates noises and then generates the final clean image by a sampling algorithm.
  arXiv  Detail & Related papers  (2023-08-17T01:59:59Z)
• Low-Light Image Enhancement with Wavelet-based Diffusion Models [50.632343822790006]
  Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration. We propose a robust and efficient Diffusion-based Low-Light image enhancement approach, dubbed DiffLL.
  arXiv  Detail & Related papers  (2023-06-01T03:08:28Z)
• Denoising Diffusion Models for Plug-and-Play Image Restoration [135.6359475784627]
  This paper proposes DiffPIR, which integrates the traditional plug-and-play method into the diffusion sampling framework. Compared to plug-and-play IR methods that rely on discriminative Gaussian denoisers, DiffPIR is expected to inherit the generative ability of diffusion models.
  arXiv  Detail & Related papers  (2023-05-15T20:24:38Z)
• DDS2M: Self-Supervised Denoising Diffusion Spatio-Spectral Model for Hyperspectral Image Restoration [103.79030498369319]
  Self-supervised diffusion model for hyperspectral image restoration is proposed. textttDDS2M enjoys stronger ability to generalization compared to existing diffusion-based methods. Experiments on HSI denoising, noisy HSI completion and super-resolution on a variety of HSIs demonstrate textttDDS2M's superiority over the existing task-specific state-of-the-arts.
  arXiv  Detail & Related papers  (2023-03-12T14:57:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.