SCoRe: Clean Image Generation from Diffusion Models Trained on Noisy Images

• URL: http://arxiv.org/abs/2604.09436v1
• Date: Fri, 10 Apr 2026 15:51:57 GMT
• Title: SCoRe: Clean Image Generation from Diffusion Models Trained on Noisy Images
• Abstract summary: Diffusion models trained on noisy datasets reproduce high-frequency training artifacts, significantly degrading generation quality.<n>We propose SCoRe, a training-free, generation-time spectral regeneration method for clean image generation from diffusion models trained on noisy images.
• Score: 6.735480539143566
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Diffusion models trained on noisy datasets often reproduce high-frequency training artifacts, significantly degrading generation quality. To address this, we propose SCoRe (Spectral Cutoff Regeneration), a training-free, generation-time spectral regeneration method for clean image generation from diffusion models trained on noisy images. Leveraging the spectral bias of diffusion models, which infer high-frequency details from low-frequency cues, SCoRe suppresses corrupted high-frequency components of a generated image via a frequency cutoff and regenerates them via SDEdit. Crucially, we derive a theoretical mapping between the cutoff frequency and the SDEdit initialization timestep based on Radially Averaged Power Spectral Density (RAPSD), which prevents excessive noise injection during regeneration. Experiments on synthetic (CIFAR-10) and real-world (SIDD) noisy datasets demonstrate that SCoRe substantially outperforms post-processing and noise-robust baselines, restoring samples closer to clean image distributions without any retraining or fine-tuning.

Related papers

• HNDiff: Haze-Noise Diffusion for Image Dehazing [52.34718859688771]
  Haze-Noise Diffusion (HNDiff) is a novel diffusion framework that embeds the atmospheric scattering model as an inductive bias.<n>In its forward process, we introduce joint haze-noise diffusion with a haze-aware noise scheduler, which progressively adds both haze and noise to an image.<n>In the reverse process, we derive a physically consistent dehazing-denoising process that simultaneously removes haze and noise to restore a clean image.
  arXiv  Detail & Related papers  (2026-08-11T14:47:38Z)
• Class-frequency Guided Noise Schedule for Diffusion Models [83.19018650759415]
  We first examine the correlations between class frequency and the multi-scale noise schedule within diffusion models.<n>We propose the textitClass-frequency Guided (CFRG) noise schedule, leveraging the insight that low-frequency classes should be endowed with larger-scale noises.
  arXiv  Detail & Related papers  (2026-06-26T03:43:23Z)
• Spectral Progressive Diffusion for Efficient Image and Video Generation [38.48147404244147]
  We propose a general framework that progressively grows resolution along the denoising trajectory of pretrained diffusion models.<n>Our framework supports training-free acceleration and a novel fine-tuning recipe that further improves efficiency and quality.
  arXiv  Detail & Related papers  (2026-05-18T17:55:39Z)
• HDW-SR: High-Frequency Guided Diffusion Model based on Wavelet Decomposition for Image Super-Resolution [4.388490927225987]
  We propose a High-Frequency Guided Diffusion Network based on Wavelet Decomposition (HDW-SR)<n>We perform diffusion only on the residual map, allowing the network to focus more effectively on high-frequency information restoration.<n> Experiments on both synthetic and real-world datasets demonstrate that HDW-SR achieves competitive super-resolution performance.
  arXiv  Detail & Related papers  (2025-11-17T09:25:26Z)
• Higher fidelity perceptual image and video compression with a latent conditioned residual denoising diffusion model [55.2480439325792]
  We propose a hybrid compression scheme optimized for perceptual quality, extending the approach of the CDC model with a decoder network.<n>We achieve up to +2dB PSNR fidelity improvements while maintaining comparable LPIPS and FID perceptual scores when compared with CDC.
  arXiv  Detail & Related papers  (2025-05-19T14:13:14Z)
• Denoising Score Distillation: From Noisy Diffusion Pretraining to One-Step High-Quality Generation [82.39763984380625]
  We introduce denoising score distillation (DSD), a surprisingly effective and novel approach for training high-quality generative models from low-quality data.<n>DSD pretrains a diffusion model exclusively on noisy, corrupted samples and then distills it into a one-step generator capable of producing refined, clean outputs.
  arXiv  Detail & Related papers  (2025-03-10T17:44:46Z)
• FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Error [16.185085063881772]
  diffusion models struggle to accurately reconstruct mid-band frequency information in real images.<n>Fire-guided Reconstruction Error is first to investigate influence of frequency decomposition on reconstruction error.<n>Experiments show that FIRE generalizes effectively to unseen diffusion models and maintains robustness against diverse perturbations.
  arXiv  Detail & Related papers  (2024-12-10T03:02:34Z)
• Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise [34.65659277870287]
  Research on denoising diffusion models has expanded its application to the field of image restoration. We propose Resfusion, a framework that incorporates the residual term into the diffusion forward process. We show that Resfusion exhibits competitive performance on ISTD dataset, LOL dataset and Raindrop dataset with only five sampling steps.
  arXiv  Detail & Related papers  (2023-11-25T02:09:38Z)
• Reconstruct-and-Generate Diffusion Model for Detail-Preserving Image Denoising [16.43285056788183]
  We propose a novel approach called the Reconstruct-and-Generate Diffusion Model (RnG) Our method leverages a reconstructive denoising network to recover the majority of the underlying clean signal. It employs a diffusion algorithm to generate residual high-frequency details, thereby enhancing visual quality.
  arXiv  Detail & Related papers  (2023-09-19T16:01:20Z)
• VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation [88.49030739715701]
  This work presents a decomposed diffusion process via resolving the per-frame noise into a base noise that is shared among all frames and a residual noise that varies along the time axis. Experiments on various datasets confirm that our approach, termed as VideoFusion, surpasses both GAN-based and diffusion-based alternatives in high-quality video generation.
  arXiv  Detail & Related papers  (2023-03-15T02:16:39Z)
• SAR Despeckling using a Denoising Diffusion Probabilistic Model [52.25981472415249]
  The presence of speckle degrades the image quality and adversely affects the performance of SAR image understanding applications. We introduce SAR-DDPM, a denoising diffusion probabilistic model for SAR despeckling. The proposed method achieves significant improvements in both quantitative and qualitative results over the state-of-the-art despeckling methods.
  arXiv  Detail & Related papers  (2022-06-09T14:00:26Z)
• Blur, Noise, and Compression Robust Generative Adversarial Networks [85.68632778835253]
  We propose blur, noise, and compression robust GAN (BNCR-GAN) to learn a clean image generator directly from degraded images. Inspired by NR-GAN, BNCR-GAN uses a multiple-generator model composed of image, blur- Kernel, noise, and quality-factor generators. We demonstrate the effectiveness of BNCR-GAN through large-scale comparative studies on CIFAR-10 and a generality analysis on FFHQ.
  arXiv  Detail & Related papers  (2020-03-17T17:56:22Z)

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.