Decomposition Ascribed Synergistic Learning for Unified Image Restoration

TL;DR

This paper introduces DASL, a unified image restoration framework that leverages singular value decomposition to decompose and optimize multiple degradation types simultaneously, improving restoration performance.

Contribution

The paper proposes a novel decomposition-based approach with SVEO and SVAO operators, enabling synergistic learning across diverse image restoration tasks.

Findings

Effective on five different image restoration tasks

Outperforms existing independent task methods

Lightweight integration into existing models

Abstract

Learning to restore multiple image degradations within a single model is quite beneficial for real-world applications. Nevertheless, existing works typically concentrate on regarding each degradation independently, while their relationship has been less exploited to ensure the synergistic learning. To this end, we revisit the diverse degradations through the lens of singular value decomposition, with the observation that the decomposed singular vectors and singular values naturally undertake the different types of degradation information, dividing various restoration tasks into two groups, \ie, singular vector dominated and singular value dominated. The above analysis renders a more unified perspective to ascribe the diverse degradations, compared to previous task-level independent learning. The dedicated optimization of degraded singular vectors and singular values inherently utilizes the potential relationship among diverse restoration tasks, attributing to the Decomposition Ascribed Synergistic Learning (DASL). Specifically, DASL comprises two effective operators, namely, Singular VEctor Operator (SVEO) and Singular VAlue Operator (SVAO), to favor the decomposed optimization, which can be lightly integrated into existing image restoration backbone. Moreover, the congruous decomposition loss has been devised for auxiliary. Extensive experiments on blended five image restoration tasks demonstrate the effectiveness of our method.