報告人：汪祥 教授
報告題目：A Bayesian Deep Prior-Based Quaternion Matrix Completion for Color Image Inpainting
報告時間：2025年12月6日（周六）下午3：00
報告地點：云龍校區(qū)6號樓304會議室
主辦單位：數(shù)學與統(tǒng)計學院、數(shù)學研究院、科學技術(shù)研究院
報告人簡介：
汪祥，博士、教授、博士生導師，現(xiàn)任南昌大學數(shù)學與計算機學院副院長，南昌大學數(shù)學一級學科博士學位點和博士后科研流動站負責人。獲批多個省級人才稱號，擔任中國計算數(shù)學分會理事，中國高等教育學會教育數(shù)學專委會常務理事, 國家天元數(shù)學東南中心江西基地執(zhí)行主任，國際知名期刊《Computational and Applied Mathematics》的副主編。主要從事數(shù)值代數(shù)、人工智能與數(shù)據(jù)科學等領域的研究，在大規(guī)模稀疏特征值問題、線性和非線性矩陣方程的數(shù)值求解、譜聚類等方面取得了一些成果。目前主持(含完成)國家自然科學基金4項及省部級項目十幾項。近幾年以第一作者或通訊作者在ACM、JSC、CCP、NLAA等權(quán)威期刊上共發(fā)表SCI收錄論文80多篇。以第一完成人身份獲江西省自然科學獎1項和江西省教學成果獎3項。
報告摘要：
Color image inpainting plays an important role in computer vision, which aims to reconstruct missing regions from the available information. Existing quaternion-based deep inpainting methods often struggle to restore both global structure and natural textures, especially when only a single corrupted image is available for training. To address these challenges, we propose BQAE-TV, a novel model that integrates a quaternion fully connected network to capture global features while incorporating total variation regularization to optimize quaternion matrix completion, producing structurally coherent and visually natural images. Furthermore, a Bayesian inference mechanism is employed to regularize the deep image prior and mitigate overfitting. Experiments demonstrate that BQAE-TV outperforms both traditional and state-of the-art methods in terms of visual quality and quantitative metrics, validating its effectiveness and robustness.