GRIDS: Grouped Multiple-Degradation Restoration with Image Degradation Similarity

TL;DR

GRIDS introduces a novel grouped restoration approach that leverages degradation similarity to improve multi-degradation image restoration, achieving significant performance gains and adaptive inference without explicit degradation classification.

Contribution

The paper proposes a new method that groups similar image degradations using statistical modeling, enhancing restoration efficiency and effectiveness over traditional single-task methods.

Findings

Grouped 11 degradation types into 4 cohesive groups

Achieved an average of 0.09dB improvement over single-task models

Improved restoration performance by 2.24dB over baseline models

Abstract

Traditional single-task image restoration methods excel in handling specific degradation types but struggle with multiple degradations. To address this limitation, we propose Grouped Restoration with Image Degradation Similarity (GRIDS), a novel approach that harmonizes the competing objectives inherent in multiple-degradation restoration. We first introduce a quantitative method for assessing relationships between image degradations using statistical modeling of deep degradation representations. This analysis facilitates the strategic grouping of similar tasks, enhancing both the efficiency and effectiveness of the restoration process. Based on the degradation similarity, GRIDS divides restoration tasks into one of the optimal groups, where tasks within the same group are highly correlated. For instance, GRIDS effectively groups 11 degradation types into 4 cohesive groups. Trained models within each group show significant improvements, with an average improvement of 0.09dB over single-task upper bound models and 2.24dB over the mix-training baseline model. GRIDS incorporates an adaptive model selection mechanism for inference, automatically selecting the appropriate grouped-training model based on the input degradation. This mechanism is particularly useful for real-world scenarios with unknown degradations as it does not rely on explicit degradation classification modules. Furthermore, our method can predict model generalization ability without the need for network inference, providing valuable insights for practitioners.