图像修复

Gruop

关于团队小组简介-图像修复

我们是图像修复组，主要从事图象遮挡修复、去噪等工作。

成员

毕业生（数据自2019年）

论文

2026

[1]

李慧, 陶泽泽, 彭锦佳.

新质生产力发展背景下的人工智能“四新四有”人才培养模式[J].

中国高校科技,2026,(01):93-98. 核心

[2]

Tan Jican, Li Kunze, Li Hui, Peng Jinjia.

Bidirectional Knowledge Distillation for Unsupervised Lifelong Person Re-identification.

PRCV (16) 2025: 172-186. SCI CCF A

2025

[3]

Tao Zeze, Li Hui, Peng Jinjia, et al.

Global Aggregated Gradient-guided Adversarial Attacks for Person Re-identification.

Pattern Recognit. SCI 中科院1区Top

[4]

He Xiaorui(何晓芮) ,Peng Jinjia(彭锦佳) ,Wang Zhen, Li Hui, Wang Huibing.

FedDSKI: Improving server-side model via dual-stage knowledge isolation in personalized federated learning[J].

Future Generation Computer Systems,2026,175108061-108061. SCI 中科院2区

[5]

李慧,陶泽泽,彭锦佳.

以强化科研素养为导向的人工智能创新人才培养模式[J].

高等工程教育研究,2025,(05):39-45. CSSCI

[6]

Liu Haibo, Lu Hancheng, Li Hui, Wang Liang, Peng Jinjia.

Multi-pattern Joint Denoising Diffusion Model for Sequential Recommendation.

ICONIP (5) 2024: 447-461. SCI

[7]

Peng Jinjia(彭锦佳), Mengkai Li(李梦凯), Huibing Wang.

Stabilizing Holistic Semantics in Diffusion Bridge for Image Inpainting.

Proceedings of 34th International Conference on International Joint Conferences on Artificial Intelligence. SCI CCF A

[8]

齐玉亮,王伟明,王静,熊彦臻,李慧.

基于跨层注意力与多记忆单元的车辆重识别方法[J].

河北大学学报(自然科学版),2025,45(03):327-336. 核心

[9]

Peng Jinjia(彭锦佳), Li Mengkai(李梦凯), Wang Bingyan(王丙彦), et al.

Omni Contextual Aggregation Networks for High-Fidelity Image Inpainting.

IEEE Transactions on Circuits and Systems for Video Technology(2025). SCI 中科院1区

2024

[10]

Cheng Tianhang (程天航), Peng Jinjia(彭锦佳,通讯), Li Hui(李慧), Wang Huibing.

Large-scale multi-view subspace clustering via embedding space and partition matrix.

Neurocomputing 602: 128266 (2024). SCI 中科院2区,JCR Q1

[11]

Peng Jinjia(彭锦佳), Yu Jiazuo(于佳左), Wang Chengjun(王铖俊), Wang Huibing, Fu Xianping.

Adapt Only Once: Fast Unsupervised Person Re-identification via Relevance-aware Guidance.

Pattern Recognition 150: 110360 (2024). SCI 中科院1区

[12]

Wang Bingyan(王丙彦), Peng Jinjia(彭锦佳,通讯), Li Hui(李慧), Wang Huibing.

Generating high-quality texture via panoramic feature aggregation for large mask inpainting.

Knowledge-Based Systems 286: 111382 (2024). SCI 中科院1区

[13]

Peng Jinjia(彭锦佳), Song Pengpeng(宋鹏鹏), Li Hui(李慧), Wang Huibing.

ReFID: Reciprocal Frequency-aware Generalizable Person Re-identification via Decomposition and Filtering.

ACM Transactions on Multimedia Computing Communications and Applications 20(7): 205:1-205:20 (2024). SCI CCF B

2023

[14]

Wang Zhiwen(王志文), Li Kai(李凯,通讯), Peng Jinjia(彭锦佳).

Dynamic context-driven progressive image inpainting with auxiliary generative units.

The Visual Computer 40(5): 3457-3472 (2024). SCI 中科院3区,JCR Q2

[15]

Yu Jiazu(于佳左), Peng Jinjia(彭锦佳,通讯), Li Kai(李凯), Wang Huibing.

Hybrid partial-constrained learning with orthogonality regularization for unsupervised person re-identification.

Engineering Applications of Artificial Intelligence 123(Part A): 106200 (2023). SCI 中科院2区,JCR Q1

[16]

Peng Jinjia(彭锦佳), Yu Jiazuo(于佳左), Jiang Guangqi, Wang Huibing, Qi Jing.

Joint learning with diverse knowledge for re-identification.

Signal Processing: Image Communication 113: 116922 (2023). SCI 中科院3区,JCR Q2

[17]

李凯,张辉,崔丽娟,彭锦佳,陈泰熙.

基于双域信息的深度残差网络图像去噪[J].

河北大学学报(自然科学版),2023,43(02):216-224. 核心

2022

[18]

Yu Jiazuo(于佳左), Li Kai(李凯,通讯), Peng Jinjia(彭锦佳).

Reference-guided face inpainting with reference attention network.

Neural Computing and Applications, Neural Computing and Applications 34(12): 9717-9731 (2022). SCI 中科院3区

2019

[19]

李凯,李慧.

基于pinball损失的结构模糊孪生支持向量机.

电子学报,2019,47(10):2221–2227. EI

专利/软著

2024-03-29

一种车辆重识别装置，申请号202322481988.5

实用新型专利

2023-06-25

一种基于桥接网络知识回顾的终身行人重识别方法，申请号202310749036.9

发明专利

2023-05-09

基于深度学习的人脸图像遮挡修复算法及其应用研究，申请号202111286793.4

发明专利

2023-01-17

基于分组感知标签的自适应记忆无监督行人重识别方法，申请号202210089329.4

发明专利

2022-04-28

基于深度学习的图像修复软件(2022SR0541326)

软件著作权

2021

基于YOLOv5算法的实时目标检测与处理系统

软件著作权

2021

基于鱼眼双目传感器的无人机室内定位系统

软件著作权

智能引领未来

河北大学网络空间安全与计算机学院

智能感知与信息处理实验室

点击量 333575