Mixed Degradation Image Restoration via Local Dynamic Optimization and Conditional Embedding

TL;DR

This paper introduces a novel image restoration model capable of handling both single and mixed degradations by dynamically adapting to diverse degradation types and guiding the restoration process with conditional feature embeddings, achieving state-of-the-art results.

Contribution

The paper proposes a new IR model with Local Dynamic Optimization and Conditional Feature Embedding modules to effectively restore images with mixed degradations, addressing diversity and singularity challenges.

Findings

Achieves SOTA performance on mixed degradation restoration.

Performs well on traditional single-task benchmarks.

Introduces a new dataset for mixed degradation scenarios.

Abstract

Multiple-in-one image restoration (IR) has made significant progress, aiming to handle all types of single degraded image restoration with a single model. However, in real-world scenarios, images often suffer from combinations of multiple degradation factors. Existing multiple-in-one IR models encounter challenges related to degradation diversity and prompt singularity when addressing this issue. In this paper, we propose a novel multiple-in-one IR model that can effectively restore images with both single and mixed degradations. To address degradation diversity, we design a Local Dynamic Optimization (LDO) module which dynamically processes degraded areas of varying types and granularities. To tackle the prompt singularity issue, we develop an efficient Conditional Feature Embedding (CFE) module that guides the decoder in leveraging degradation-type-related features, significantly improving the model's performance in mixed degradation restoration scenarios. To validate the effectiveness of our model, we introduce a new dataset containing both single and mixed degradation elements. Experimental results demonstrate that our proposed model achieves state-of-the-art (SOTA) performance not only on mixed degradation tasks but also on classic single-task restoration benchmarks.