DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:SQHJZVSMrecord.jsonopen to challenge →
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
HiTokSR: A Coarse-to-Fine Tokenizer with Hierarchical Codebooks for High-Fidelity Real-World Image Super-Resolution
HiTokSR uses a coarse-to-fine hierarchical tokenizer with frequency-aware sub-codebooks, vision foundation model priors, and index perturbation to achieve state-of-the-art perceptual quality and fidelity in real-world...
-
GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration
GGT-100K is a 103k-pair LQ-HQ dataset generated via MFMs to enhance real-world generalization of image restoration models.
-
VARestorer: One-Step VAR Distillation for Real-World Image Super-Resolution
VARestorer converts a text-to-image VAR model into a fast one-step real-world image super-resolution model via distribution matching distillation and pyramid image conditioning.
-
EAM: Enhancing Anything with Diffusion Transformers for Blind Super-Resolution
EAM is a DiT-based blind super-resolution model that uses a triple-flow Ψ-DiT block, progressive masked image modeling, and in-context subject-aware prompting to reach state-of-the-art quantitative and visual results ...
-
Segment Any-Quality Images with Generative Latent Space Enhancement
GleSAM integrates latent diffusion into SAM and SAM2 to boost segmentation robustness on low-quality images using minimal extra parameters and a new LQSeg dataset.
-
Towards Any-Quality Image Segmentation via Generative and Adaptive Latent Space Enhancement
GleSAM++ improves SAM robustness on degraded images by using generative enhancement, feature alignment, and adaptive degradation prediction while adding few parameters.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.