个人简介：

    程日，福州大学计算机与大数据学院副教授，福建省引进生，现任职于福建省网络计算与智能信息处理重点实验室。2025 年获复旦大学计算机科学与技术博士学位，获复旦大学优秀毕业生荣誉；此前于 2020 年获厦门大学软件工程学士学位。主要研究方向包括低层视觉、图像增强、图像融合、语义分割、数据安全、多模态学习与 AI for Science 等。研究兴趣集中在面向复杂真实场景的视觉感知与智能计算方法，重点关注如何提升图像/视频在低质量、跨模态、多源异构、数据受限或安全敏感场景下的表示、增强、重建与理解能力。相关研究可应用于真实场景图像增强、科学成像、医学/生命科学图像分析、遥感与红外感知、多模态智能系统等方向。近年来，相关研究成果发表在 Nature Photonics、CVPR、AAAI、ACM MM、ICME 等重要国际期刊和会议上，研究内容涉及实时体内多光谱成像、时空超分辨率、图像与视频重建、光流估计、图像篡改定位、伪装目标检测、多视角图像超分辨等方向。担任 CVPR、ICCV、ECCV、AAAI、ACM MM 等国际会议审稿人。

个人主页：

https://richeng-web.github.io/

联系邮箱：

rcheng@fzu.edu.cn

招生信息：

目前2027级硕士招生专业：计算机科学与技术、软件工程、计算机应用、人工智能等。

    希望申请同学具备以下特质：

        科研兴趣明确：愿意认真阅读论文、思考问题、持续推进课题。

        编程能力较好：熟悉 Python，具备一定深度学习框架使用经验，如 PyTorch。

        英语阅读与AI工具使用能力较好：能够阅读英文论文，善于使用 AI 工具辅助文献检索、论文阅读、代码实现和实验分析，并保持独立思考。

        沟通主动、执行力强：认真参与每周组会和课题讨论，共同推进课题，及时反馈问题。

        身心健康、积极向上：能够平衡科研压力与长期成长，保持稳定、认真和开放的学习态度。

科研成果：

Niu Y, Wang Y, Cheng R†, et al. Modality-Specific Hierarchical Enhancement for RGB-D Camouflaged Object Detection[J]. ICME 2026.

Lu Zhang*, Ri Cheng*, et al. Excitation-encoded single-emission shortwave infrared lanthanide fluorophore palette for real-time in vivo multispectral imaging[J]. Nature Photonics, 2025: 1-10, (IF:38.2).

Ruian He, Ri Cheng, Xinkai Lyu, Weimin Tan, and Bo Yan. Efficient Online Training for Zero-Shot Time-Lapse Microscopy Denoising and Super-Resolution//Proceedings of the AAAI Conference on Artificial Intelligence AAAI 2025,

He R, Zhang Z, Cheng R, et al. Efficient Trajectory Space-Time Super-Resolution for Fast Live-cell Imaging[C]//Proceedings of the 33rd ACM International Conference on Multimedia. 2025: 171-179. ACM MM 2025.

Zeng Kunlun*, Ri Cheng*, Weimin Tan and Bo Yan.MGQFormer: Mask-Guided Query-Based Transformer for Image Manipulation Localization//Proceedings of the AAAI Conference on Artificial Intelligence, AAAI 2024.  

Ri Cheng, Ruian He, Xuhao Jiang, Shili Zhou, Weimin Tan, and Bo Yan. Context-Aware Iteration Policy Network for Efficient Optical Flow Estimation[C]//Proceedings of the AAAI Conference on Artificial Intelligence, AAAI 2024.  

Ruian He, Shili Zhou, Sun Yuqi, Ri Cheng, Weimin Tan, and Bo Yan. Low-Latency Space-Time Supersampling for Real-Time Rendering//Proceedings of the AAAI Conference on Artificial Intelligence, AAAI 2024.

Ri Cheng, Xuhao Jiang, Ruian He, Shili Zhou, Weimin Tan, and Bo Yan. Uncertainty-Guided Spatial Pruning Architecture for Efficient Frame Interpolation//Proceedings of the 31st ACM International Conference on Multimedia, ACM MM 2023.  

Ruian He, Shili Zhou, Ri Cheng, Sun Yuqi, Weimin Tan, and Bo Yan.Motion Matters: Difference-based Multi-scale Learning for Infrared UAV Detection//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPRW 2023.

Ri Cheng, Sun Yuqi, Bo Yan, Weimin Tan, and Chenxi Ma. Geometry-aware reference synthesis for multi-view image super-resolution//Proceedings of the 30th ACM International Conference on Multimedia, ACM MM 2022,

Xuhao Jiang, Weimin Tan, Ri Cheng, Shili Zhou, and Yan, Bo. Learning parallax transformer network for stereo image jpeg artifacts removal//Proceedings of the 30th ACM International Conference on Multimedia,ACM MM 2022,  

Sun Yuqi, Shili Zhou, Ri Cheng, Weimin Tan, Bo Yan, and Lang Fu. Learning robust image-based rendering on sparse scene geometry via depth completion//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022.  

Sun Yuqi*, Ri Cheng*, Bo Yan, and Shili Zhou.Space-Angle Super-Resolution for Multi-View Images//Proceedings of the 29th ACM International Conference on Multimedia, ACM MM 2021