付刚

2016-2021   武汉大学 计算机应用技术 博士

2026-今    吉林大学 教授 博导

2022-2025   香港理工大学 研究员

研究方向涵盖计算机视觉、深度学习及人工智能。特别地，围绕复杂环境下的视觉感知与光照机理建模开展研究，融合数据驱动方法与物理约束思想，探索具有泛化能力与可解释性的视觉智能模型。具体研究内容重点包括：

1. 复杂环境图像复原与增强。针对低照度、强反射、阴影遮挡及未知退化等问题，研究面向开放场景的图像与视频复原方法，提升模型在真实环境中的鲁棒性与跨场景适应能力。

2. 光照分析与物理一致性建模。研究光照分解、重光照与光照迁移等问题，分析光照与反射率、几何结构之间的耦合关系，设计兼具物理一致性与数据驱动优势的光照建模方法。

3. 面向多模态与智能体的光照感知建模。探索光照信息在跨模态理解与环境推理中的表达形式与作用机制，将光照感知能力融入智能决策与生成过程，增强系统在复杂场景中的综合感知能力。

正在招募博士后、博士生（每年2-3名）、硕士生（每年3-4名）、科研助理和实习生。实验室提供充足的硬件设备、实验场地等良好的科研条件。欢迎有志于科研的同学加入，共同探索计算机视觉、深度学习、人工智能等领域的前沿问题。有意者通过邮箱联系我并发送个人简历。

付刚，吉林大学教授、博士生导师，国家高层次青年人才。主要从事计算机视觉、深度学习及人工智能等方面的研究，近年来在IJCV、CVPR、ICCV、ECCV等国际计算机视觉与人工智能顶级期刊和会议上发表论文30余篇。

代表性论文：

1. [反光检测与消除] Gang Fu, Qing Zhang, Lei Zhu, Ping Li, and Chunxia Xiao. "A multi-task network for joint specular highlight detection and removal." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7752-7761. 2021.

2. [反光消除] Gang Fu. "Neural solver of dichromatic reflection model for specular highlight removal." In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 7241-7250. 2025.

3. [反光消除] Gang Fu, Qing Zhang, Lei Zhu, Chunxia Xiao, and Ping Li. "Towards high-quality specular highlight removal by leveraging large-scale synthetic data." In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 12857-12865. 2023.

4. [反光检测] Gang Fu, Qing Zhang, Lei Zhu, Qifeng Lin, Yihao Wang, Siyuan Fan, and Chunxia Xiao. "Towards high-resolution specular highlight detection." International Journal of Computer Vision (IJCV) 132, no. 1 (2024): 95-117.

5. [阴影检测与消除] Xinyun Fan, Wenjun Wu, Ling Zhang, Qingan Yan, Gang Fu, Zipei Chen, Chengjiang Long, and Chunxia Xiao. "Shading-aware shadow detection and removal from a single image." The Visual Computer 36, no. 10 (2020): 2175-2188.

6. [本征分解] Gang Fu, Qing Zhang, and Chunxia Xiao. "Towards high-quality intrinsic images in the wild." In Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), pp. 175-180. 2019.

7. [重光照] Zhongyun Bao, Gang Fu, Jianchi Sun, Jing Zhou, Ziqi Yu, and Chunxia Xiao. "I2HDiffuser: Image illumination harmonization meets the diffusion model." In Proceedings of the ACM International Conference on Multimedia (ACM MM), pp. 1627-1636. 2025.

8. [图像复原] Cong Wang, Jinshan Pan, Wei Wang, Gang Fu, Siyuan Liang, Mengzhu Wang, Xiao-Ming Wu, and Jun Liu. "Correlation matching transformation transformers for uhd image restoration." In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 5336-5344. 2024.

9. [风格迁移] Hong Ding, Fei Luo, Caoqing Jiang, Gang Fu, Zipei Chen, Shenghong Hu, and Chunxia Xiao. "Photorealistic style transfer via adaptive filtering and channel seperation." In Proceedings of the ACM International Conference on Multimedia (ACM MM), pp. 2627-2635. 2022.

10. [目标检测] Qifeng Lin, Luojun Lin, Yulong Yuan, and Gang Fu. "A multiple prediction mechanisms ensemble for complex remote sensing scenes." In Proceedings of the ACM International Conference on Multimedia (ACM MM), pp. 8635-8643. 2023.