Spatial-and-Frequency-aware Restoration method for Images based on Diffusion Models
On the map: Diffusion models → Inverse problems and image restoration
Abstract (arXiv)
Diffusion models have recently emerged as a promising framework for Image Restoration (IR), owing to their ability to produce high-quality reconstructions and their compatibility with established methods. Existing methods for solving noisy inverse problems in IR, considers the pixel-wise data-fidelity. In this paper, we propose SaFaRI, a spatial-and-frequency-aware diffusion model for IR with Gaussian noise. Our model encourages images to preserve data-fidelity in both the spatial and frequency domains, resulting in enhanced reconstruction quality. We comprehensively evaluate the performance of our model on a variety of noisy inverse problems, including inpainting, denoising, and super-resolution. Our thorough evaluation demonstrates that SaFaRI achieves state-of-the-art performance on both the ImageNet datasets and FFHQ datasets, outperforming existing zero-shot IR methods in terms of LPIPS and FID metrics.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 26 of its 42 references that are in the map. First posted on arXiv 31 Jan 2024.
Builds on
26 of 42 references.
Closest ancestors · 8
Same direction, newest first
- 2023Denoising Diffusion Models for Plug-and-Play Image Restoration15 May
- 2023Generative Diffusion Prior for Unified Image Restoration and Enhancement3 Apr
- 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model1 Dec
- 2022Diffusion Posterior Sampling for General Noisy Inverse Problems29 Sep
- 2022JPEG Artifact Correction using Denoising Diffusion Restoration Models23 Sep
- 2022Improving Diffusion Models for Inverse Problems using Manifold Constraints2 Jun
- 2022Denoising Diffusion Restoration Models27 Jan
- 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction9 Dec
Other references · 18
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
- 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
- 2021Image Super-Resolution via Iterative Refinementcited by 1,506
- 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
- 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
- 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 634
- 2016Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applicationscited by 244
- 2022Diffusion models as plug-and-play priorscited by 230
6 more
- 2021SNIPS: Solving Noisy Inverse Problems Stochasticallycited by 191
- 2022Diffusion Probabilistic Model Made Slimcited by 121
- 2021Fourier Space Losses for Efficient Perceptual Image Super-Resolutioncited by 72
- 2017Perceptual Adversarial Networks for Image-to-Image Transformationcited by 42
- 2020R-MNet: A Perceptual Adversarial Network for Image Inpaintingcited by 12
- 2023Spatial-Frequency U-Net for Denoising Diffusion Probabilistic Modelscited by 7
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Frequency-Guided Posterior Sampling for Diffusion-Based Image Restoration
- 2024Taming Diffusion Models for Image Restoration: A Review
- 2024Blind Image Restoration via Fast Diffusion Inversion
- 2023Unlimited-Size Diffusion Restoration
- 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey
- 2024Efficient Diffusion Model for Image Restoration by Residual Shifting
- 2026NFCDS: A Plug-and-Play Noise Frequency-Controlled Diffusion Sampling Strategy for Image Restoration
- 2025Zero-Shot Solving of Imaging Inverse Problems via Noise-Refined Likelihood Guided Diffusion Models