DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior

TL;DR

DiffBIR introduces a unified blind image restoration framework that separates degradation removal from content regeneration, utilizing generative diffusion models for realistic detail synthesis and adjustable guidance for balanced results.

Contribution

The paper proposes a novel two-stage blind image restoration pipeline using diffusion models, enabling flexible, high-quality restoration across multiple tasks.

Findings

Outperforms state-of-the-art methods in blind super-resolution, face restoration, and denoising.

Effective region-adaptive guidance allows user-controlled balance between realism and fidelity.

Demonstrates robustness on both synthetic and real-world datasets.

Abstract

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.