Restorer: Removing Multi-Degradation with All-Axis Attention and Prompt Guidance

TL;DR

Restorer is a Transformer-based all-in-one image restoration model that uses All-Axis Attention and prompt guidance to effectively handle complex, real-world degradations without needing multiple models or additional training.

Contribution

The paper introduces Restorer, a novel model with All-Axis Attention and prompt-based task priors, enabling versatile, efficient, and state-of-the-art image restoration across multiple degradation types.

Findings

Achieves state-of-the-art performance on multiple restoration tasks.

Handles composite degradations without additional training.

Efficient inference suitable for real-world applications.

Abstract

There are many excellent solutions in image restoration.However, most methods require on training separate models to restore images with different types of degradation.Although existing all-in-one models effectively address multiple types of degradation simultaneously, their performance in real-world scenarios is still constrained by the task confusion problem.In this work, we attempt to address this issue by introducing \textbf{Restorer}, a novel Transformer-based all-in-one image restoration model.To effectively address the complex degradation present in real-world images, we propose All-Axis Attention (AAA), a mechanism that simultaneously models long-range dependencies across both spatial and channel dimensions, capturing potential correlations along all axes.Additionally, we introduce textual prompts in Restorer to incorporate explicit task priors, enabling the removal of specific degradation types based on user instructions. By iterating over these prompts, Restorer can handle composite degradation in real-world scenarios without requiring additional training.Based on these designs, Restorer with one set of parameters demonstrates state-of-the-art performance in multiple image restoration tasks compared to existing all-in-one and even single-task models.Additionally, Restorer is efficient during inference, suggesting the potential in real-world applications.