报告题目：A Bayesian Deep Prior-Based Quaternion Matrix Completion for Color Image Inpainting
时 间：2025年12月19日（星期五）09:30
地 点：科研楼18号楼1102
主 办：数学与统计学院
参加对象：感兴趣的老师和学生
报告摘要：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-ofthe- art methods in terms of visual quality and quantitative metrics, validating its effectiveness and robustness.
报告人简介：汪祥，博士、教授、博士生导师，现任南昌大学数学与计算机学院副院长。先后入选或获批江西省新世纪百千万人才工程人选，江西省青年科学家，江西省高等学校中青年骨干教师，江西省高水平本科教学团队负责人，南昌大学香樟英才特聘教授，宝钢全国优秀教师奖获得者；担任中国工业与应用数学学会理事，中国数学会计算数学分会理事，中国高等教育学会教育数学专委会副秘书长,国际知名期刊《Computational and Applied Mathematics》的副主编。主要从事数值代数、人工智能与数据科学等领域的研究，在大规模稀疏线性方程组、大规模稀疏特征值问题、线性和非线性矩阵方程的数值求解、谱聚类等方面取得了一些成果。目前主持(含完成)国家自然科学基金面上、地区、青年项目4项及省部级项目（含江西省杰出青年基金、江西省自然科学基金重点重大项目）十几项。近几年以第一作者或通讯作者在国内外权威期刊上共发表SCI收录论文50多篇。以第一完成人身份获江西省自然科学奖三等奖1项和江西省教学成果奖二等奖3项。