DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Xinqi, He, Jingwen, Chen, Ziyan, Lyu, Zhaoyang, Dai, Bo, Yu, Fanghua, Ouyang, Wanli, Qiao, Yu, Dong, Chao
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913310920671232
author Lin, Xinqi
He, Jingwen
Chen, Ziyan
Lyu, Zhaoyang
Dai, Bo
Yu, Fanghua
Ouyang, Wanli
Qiao, Yu
Dong, Chao
author_facet Lin, Xinqi
He, Jingwen
Chen, Ziyan
Lyu, Zhaoyang
Dai, Bo
Yu, Fanghua
Ouyang, Wanli
Qiao, Yu
Dong, Chao
contents We present DiffBIR, a general restoration pipeline that could handle different blind image restoration tasks in a unified framework. DiffBIR decouples blind image restoration problem into two stages: 1) degradation removal: removing image-independent content; 2) information regeneration: generating the lost image content. Each stage is developed independently but they work seamlessly in a cascaded manner. In the first stage, we use restoration modules to remove degradations and obtain high-fidelity restored results. For the second stage, we propose IRControlNet that leverages the generative ability of latent diffusion models to generate realistic details. Specifically, IRControlNet is trained based on specially produced condition images without distracting noisy content for stable generation performance. Moreover, we design a region-adaptive restoration guidance that can modify the denoising process during inference without model re-training, allowing users to balance realness and fidelity through a tunable guidance scale. Extensive experiments have demonstrated DiffBIR's superiority over state-of-the-art approaches for blind image super-resolution, blind face restoration and blind image denoising tasks on both synthetic and real-world datasets. The code is available at https://github.com/XPixelGroup/DiffBIR.
format Preprint
id arxiv_https___arxiv_org_abs_2308_15070
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior
Lin, Xinqi
He, Jingwen
Chen, Ziyan
Lyu, Zhaoyang
Dai, Bo
Yu, Fanghua
Ouyang, Wanli
Qiao, Yu
Dong, Chao
Computer Vision and Pattern Recognition
We present DiffBIR, a general restoration pipeline that could handle different blind image restoration tasks in a unified framework. DiffBIR decouples blind image restoration problem into two stages: 1) degradation removal: removing image-independent content; 2) information regeneration: generating the lost image content. Each stage is developed independently but they work seamlessly in a cascaded manner. In the first stage, we use restoration modules to remove degradations and obtain high-fidelity restored results. For the second stage, we propose IRControlNet that leverages the generative ability of latent diffusion models to generate realistic details. Specifically, IRControlNet is trained based on specially produced condition images without distracting noisy content for stable generation performance. Moreover, we design a region-adaptive restoration guidance that can modify the denoising process during inference without model re-training, allowing users to balance realness and fidelity through a tunable guidance scale. Extensive experiments have demonstrated DiffBIR's superiority over state-of-the-art approaches for blind image super-resolution, blind face restoration and blind image denoising tasks on both synthetic and real-world datasets. The code is available at https://github.com/XPixelGroup/DiffBIR.
title DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2308.15070