DELNet: Continuous All-in-One Weather Removal via Dynamic Expert Library

TL;DR

DELNet is a continual learning framework for weather image restoration that dynamically manages expert models to efficiently handle various weather degradations without retraining, outperforming existing methods.

Contribution

It introduces a novel dynamic expert library and task similarity judging mechanism for continuous weather image restoration without retraining existing models.

Findings

DELNet achieves PSNR gains of up to 16% on benchmark datasets.

It surpasses state-of-the-art continual learning methods in weather restoration.

DELNet reduces retraining costs and improves robustness.

Abstract

All-in-one weather image restoration methods are valuable in practice but depend on pre-collected data and require retraining for unseen degradations, leading to high cost. We propose DELNet, a continual learning framework for weather image restoration. DELNet integrates a judging valve that measures task similarity to distinguish new from known tasks, and a dynamic expert library that stores experts trained on different degradations. For new tasks, the valve selects top-k experts for knowledge transfer while adding new experts to capture task-specific features; for known tasks, the corresponding experts are directly reused. This design enables continuous optimization without retraining existing models. Experiments on OTS, Rain100H, and Snow100K demonstrate that DELNet surpasses state-of-the-art continual learning methods, achieving PSNR gains of 16\%, 11\%, and 12\%, respectively. These results highlight the effectiveness, robustness, and efficiency of DELNet, which reduces retraining cost and enables practical deployment in real-world scenarios.