一个模型搞定多种模糊类型，实时精准去模糊。
Towards Unified Image Deblurring using a Mixture-of-Experts Decoder
- 用专家混合解码器按模糊类型动态分配处理路径。
- 在多种模糊场景下性能媲美专用模型，且泛化能力强。
- 适合需要统一去模糊方案的实用场景，如手机摄影。
图像去模糊是计算摄影和低层计算机视觉中的基础任务。现有方法多针对特定模糊类型设计，缺乏通用性，导致需部署多个模型才能覆盖多种模糊，实用性受限。本文提出首个一体化去模糊方法，可高效恢复受全局运动、局部运动、低光模糊及散焦模糊影响的图像。设计了基于模糊退化类型识别的混合专家（MoE）解码模块，实现端到端的精准高效重建。实验表明，该方法性能接近专用模型，且对未见过的模糊场景具有优异泛化能力，尤其在合理选择专家时表现突出。代码已开源：https://github.com/cidautai/DeMoE。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。