Towards Unified Image Deblurring using a Mixture-of-Experts Decoder

TL;DR

This paper presents a novel unified image deblurring method using a mixture-of-experts decoder that adapts to various blur types, achieving comparable performance to specialized models and better generalization to unseen scenarios.

Contribution

Introduces the first all-in-one deblurring approach with a mixture-of-experts decoder that dynamically adapts to diverse blur degradations in an end-to-end framework.

Findings

Achieves performance comparable to dedicated models for specific blur types.

Demonstrates improved generalization to unseen blur scenarios.

Efficiently handles multiple blur types within a single model.

Abstract

Image deblurring, removing blurring artifacts from images, is a fundamental task in computational photography and low-level computer vision. Existing approaches focus on specialized solutions tailored to particular blur types, thus, these solutions lack generalization. This limitation in current methods implies requiring multiple models to cover several blur types, which is not practical in many real scenarios. In this paper, we introduce the first all-in-one deblurring method capable of efficiently restoring images affected by diverse blur degradations, including global motion, local motion, blur in low-light conditions, and defocus blur. We propose a mixture-of-experts (MoE) decoding module, which dynamically routes image features based on the recognized blur degradation, enabling precise and efficient restoration in an end-to-end manner. Our unified approach not only achieves performance comparable to dedicated task-specific models, but also shows promising generalization to unseen blur scenarios, particularly when leveraging appropriate expert selection. Code available at https://github.com/cidautai/DeMoE.