INDIGO+: A Unified INN-Guided Probabilistic Diffusion Algorithm for Blind and Non-Blind Image Restoration

TL;DR

INDIGO+ introduces a unified diffusion-based image restoration method guided by invertible neural networks, enabling flexible handling of both blind and non-blind degradation without relying on predefined models, achieving competitive results.

Contribution

The paper presents a novel INN-guided probabilistic diffusion algorithm that effectively addresses limitations of existing IR methods, enhancing flexibility and performance in real-world scenarios.

Findings

Achieves competitive results on synthetic and real-world images.

Effectively handles both blind and non-blind degradation.

Improves inference speed with a new initialization strategy.

Abstract

Generative diffusion models are becoming one of the most popular prior in image restoration (IR) tasks due to their remarkable ability to generate realistic natural images. Despite achieving satisfactory results, IR methods based on diffusion models present several limitations. First of all, most non-blind approaches require an analytical expression of the degradation model to guide the sampling process. Secondly, most existing blind approaches rely on families of pre-defined degradation models for training their deep networks. The above issues limit the flexibility of these approaches and so their ability to handle real-world degradation tasks. In this paper, we propose a novel INN-guided probabilistic diffusion algorithm for non-blind and blind image restoration, namely INDIGO and BlindINDIGO, which combines the merits of the perfect reconstruction property of invertible neural networks (INN) with the strong generative capabilities of pre-trained diffusion models. Specifically, we train the forward process of the INN to simulate an arbitrary degradation process and use the inverse to obtain an intermediate image that we use to guide the reverse diffusion sampling process through a gradient step. We also introduce an initialization strategy, to further improve the performance and inference speed of our algorithm. Experiments demonstrate that our algorithm obtains competitive results compared with recently leading methods both quantitatively and visually on synthetic and real-world low-quality images.