数据与计算发展前沿2026，Vol.8Issue(3)：110-121,12.DOI:10.11871/jfdc.issn.2096-742X.2026.03.010
一种基于测试时训练的跨域图像去模糊方法
A Test-Time Training Based Cross-Domain Image Deblurring Method
摘要
Abstract
[Purpose]This study aims to address the problem of cross-domain image deblurring by propos-ing a novel test-time training method.[Methods]A defocus blur generation network(DBGN)is constructed by simulating the formation process of defocus blur,which is embedded at the end of the deblurring model to create an auxiliary task.During the training phase,the DBGN serves as an additional auxiliary loss to optimize the deblurring model and enhance deblurring accuracy.In the testing phase,the DBGN is utilized to perform a re-blurring task,acting as an auxiliary module to assist the primary deblurring model in updating parameters to adapt to out-of-distribution cross-domain data.[Results]The proposed method is tested on blurred images captured in inspection scenarios,validating its practical performance for cross-domain image deblurring in real-world settings.[Conclusions]Extensive experiments on multiple public defocus blur datasets and comparisons with current state-of-the-art methods demonstrate the effectiveness of the proposed approach.关键词
图像处理/图像去模糊/测试时训练Key words
image processing/image deblurring/test-time training引用本文复制引用
褚景春,杨光俊,王文彬,高思远,高满达,张森,何勇..一种基于测试时训练的跨域图像去模糊方法[J].数据与计算发展前沿,2026,8(3):110-121,12.基金项目
国家重点研发计划青年科学家项目"互联网金融个人生物信息可信识别与隐私保护技术研究"(2022YFC3310400) （2022YFC3310400）
国家能源集团科技创新项目"火电厂人工智能运营体系典型应用场景样本库模型库研究"(GJNY-23-99) （GJNY-23-99）
