Saved in:
Bibliographic Details
Main Authors: Lee, Kyungsung, Lee, Donggyu, Kang, Myungjoo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.17629
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912719715696640
author Lee, Kyungsung
Lee, Donggyu
Kang, Myungjoo
author_facet Lee, Kyungsung
Lee, Donggyu
Kang, Myungjoo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2401_17629
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Spatial-and-Frequency-aware Restoration method for Images based on Diffusion Models
Lee, Kyungsung
Lee, Donggyu
Kang, Myungjoo
Computer Vision and Pattern Recognition
Machine Learning
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.
title Spatial-and-Frequency-aware Restoration method for Images based on Diffusion Models
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2401.17629