DRNet: All-in-One Image Restoration via Prior-Guided Dynamic Reparameterization

TL;DR

DRNet introduces a unified, efficient image restoration framework that eliminates per-input overhead, handles diverse tasks with a dynamic reparameterization approach, and leverages frequency-aware encoding for superior performance.

Contribution

The paper proposes DRNet, a novel all-in-one image restoration model with a reconfiguration paradigm, dynamic reparameterization, and frequency-aware encoding, addressing key limitations of existing methods.

Findings

Achieves state-of-the-art results across five restoration tasks.

Operates with superior parameter efficiency and flexibility.

Excels as both a foundation model and a user-guided specialist.

Abstract

All-in-one image restoration aims to handle diverse degradations within a single model. However, existing methods often suffer from three key limitations: 1) per-input computational overhead from dynamic degradation estimation; 2) optimization challenges due to task heterogeneity; and 3) inefficient, frequency-agnostic encoder designs. To overcome these, we introduce the Dynamic Reparameterization Network (DRNet), a novel framework operating on an initialization-stage reconfiguration paradigm that fundamentally eliminates per-input overhead. At its core, a Dynamic Reparameterization MLP (DRMLP) guided by a Task-Specific Modulator (TSM), which effectively mitigates task heterogeneity by orchestrating both specific restoration goals and a versatile general-purpose mode within a unified architecture. Furthermore, we incorporate a Continuous Wavelet Transform Encoder (CWTE) that explicitly leverages frequency characteristics via wavelet decomposition for a lightweight yet powerful design. Extensive experiments demonstrate that DRNet achieves state-of-the-art performance across five restoration tasks with superior parameter efficiency. Crucially, it showcases unique flexibility, excelling as both a highly competitive foundation model for blind restoration and a top-performing user-guided specialist.