研究方向：图像处理、计算成像、人工智能

研究兴趣：
。生成式图像表示模型
。涉散射介质图像处理
。神经拟态成像与感知
。高维空间贝叶斯优化
。可信可理解人工智能

相关专著：
。基于图像先验建模的超分辨增强理论与算法——变分PDE、稀疏正则化与贝叶斯方法. 国防工业出版社, 2017.

部分论文：
。FaceGCN: Structured priors inspired graph convolutional networks for blind face restoration. IEEE Trans. on Circuits and Systems for Video Technology, 2025.
。LNLFace: Enhanced blind face restoration with local and non-local lookups. International Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2025.
。M2Mamba: Multi-scale in multi-scale Mamba for blind face restoration. IEEE International Conf. on Bioinformatics and Biomedicine (BIBM), 2024.
。基于逐层增量分解的深度网络神经元相关性解释方法. 自动化学报, 2024.
。一种基于迭代累积梯度的多层特征重要性攻击方法. 电子学报, 2024.
。Revisiting the regularizers in blind image deblurring with a new one. IEEE Trans. on Image Processing, 2023.
。A type-II maximum-likelihood approach to Gaussian scale mixture-based sparse regression Kriging. Comput. & Ind. Eng., 2022.
。DeblurGAN+: Revisiting blind motion deblurring using conditional adversarial networks. Signal Processing, 2020.
。Gradient-based discriminative modeling for blind image deblurring. Neurocomputing, 2020.
。Blind deconvolution via complementarily structure-aware image smoothing. Journal of Electronic Imaging, 2020.
。On potentials of regularized Wasserstein generative adversarial networks for realistic hallucination of tiny faces. Neurocomputing, 2019.
。Nonparametric blind super‑resolution using adaptive heavy‑tailed priors. Journal of Mathematical Imaging and Vision, 2019.
。Adapting total generalized variation for blind image restoration. Multidimensional Systems and Signal Processing, 2019.
。Structure-based low-rank model with graph nuclear norm regularization for noise removal. IEEE Transactions on Image Processing, 2017.
。Regularized motion blur-kernel estimation with adaptive sparse image prior learning. Pattern Recognition, 2016.
。Hybrid active contour model with structured feature for image segmentation. Signal Processing, 2015.
。Motion deblurring using nonstationary image modeling. Journal of Mathematical Imaging and Vision, 2015.
。Bi-L0-L2-norm regularization for blind motion deblurring. Journal of Visual Communication and Image Representation, 2015.
。Kullback-Leibler divergence based composite prior modeling for Bayesian super-resolution. Journal of Scientific Computing, 2014.

部分专利：
。低清图像重建超分辨率人脸图像的方法、系统及存储介质. 202210296363.9, 授权, 2025.
。一种用于目标检测的自适应平衡训练损失的方法、装置及存储介质. 202210253989.1, 授权, 2024.
。基于边缘感知的图像盲去模糊组合稀疏优化方法. 201810325132X, 授权, 2023.
。基于线性多步残差学习的视觉感知方法及视觉感知装置. 2020104732216, 授权, 2023.
。基于多路径深度卷积神经网络的超分辨率重建方法. 2018103251315, 授权, 2022.
。基于互补结构感知的内外循环驱动图像盲去模糊方法和装置. 2021100733322, 授权, 2022.
。非受限视频监控的低清人脸识别方法、装置、设备及介质. 202110377777.X, 授权, 2022.
。基于互补结构感知的内外循环驱动图像盲去模糊方法和装置. 202110073332.2, 授权, 2022.
。一种基于多尺度的行人检测方法. 202110419108.4, 授权, 2022.
。一种域自适应雾天图像目标检测方法和装置. 202011527409.0, 授权, 2022.
。基于多路径深度卷积神经网络的超分辨重建方法. 201810325131.5, 授权, 2022.
。一种雾霾天气车载视频动态目标检测和识别的方法. 201910530766.3, 授权, 2021.
。基于可联合实现语义分割和景深估计的网络模型的装置. 202010445676.7, 授权, 2020.
。基于凹凸混合正则先验的图像盲去卷积方法. 201510964588.7, 授权, 2019.
。基于分裂Bregman迭代的快速鲁棒图像运动去模糊方法. 201410239703.X, 授权, 2018.
。基于L0稀疏先验的盲相机抖动去模糊方法. 201310362933.0, 授权, 2017.