宋天舒，副教授，硕导。主要从事人工智能图像处理与AI+Physics交叉方向的研究，入选江苏省卓越博士后计划。共以第一/通讯作者发表高水平SCI论文(JCR一区以上)10余篇，主持国家自然科学基金青年项目、江苏省自然科学基金青年项目、博士后科学基金面上项目等国家和省部级项目4项。作为骨干参与国自然面上项目、重点研发计划子课题等其它项目多项，受邀担任IEEE TPAMI、TIP、TMM、 TCSVT、ICME等多个高水平期刊和会议的审稿人。

研究方向

AI图像处理（方向简介）

大模型 (方向简介）

AI+Physics交叉研究（方向简介） 

招生方向

信息与通信工程（0810）｜学术型硕士

电子信息（0854）｜专业型硕士（含新一代信息技术、通信工程方向）

除招收研究生外，非常欢迎热爱科研、愿意深耕的本科生进组科研！

指导细致，鼓励学生以独立一作发表高水平论文，支持研究生实习。

部分项目

中国自然科学基金青年项目，主持，2026-2028

江苏省自然科学基金青年项目，主持，2025-2027

中国博士后科学基金面上项目，主持，2024-2026

江苏省卓越博士后计划，主持，2024-2026

部分成果

Tianshu Song, Deqiang Cheng*, Qiqi Kou, Sanyou Zhang, Yipo Huang, and Leida Li, “Content Understanding and Reasoning Enhanced Small-Sample Blind Image Quality Assessment”, IEEE Transactions on Multimedia, 2026 (中科院一区Top，图像处理).

Deqiang Cheng, Feiyu Chen, Tianshu Song*, Qiqi Kou, Sanyou Zhang, Leida Li, “Diversified Content and Curriculum Learning Enhanced Blind Image Quality Assessment”, IEEE Transactions on Multimedia, 2026 (中科院一区Top，图像处理).

Deqiang Cheng, Zihao Li, Tianshu Song*, Qiqi Kou, and Leida Li, “Few-Label Blind Image Quality Assessment via Samples Chosen from New and Existing Scenes”, Pattern Recognition, 2026 (中科院一区Top，图像处理).

Tianshu Song and Hui Xia*, “Numerically stable neural network for simulating Kardar-Parisi-Zhang growth in the presence of uncorrelated and correlated noises”, Computer Physics Communications, 2025 (JCR Q1，计算物理).

Tianshu Song, Leida Li*, Jinjian Wu, Weisheng Dong, and Deqiang Cheng, “Quality-aware Blind Image Motion Deblurring”, Pattern Recognition, 2024 (中科院一区Top，图像处理).

Tianshu Song, Leida Li*, Deqiang Cheng*, Pengfei Chen, and Jinjian Wu, “Active Learning-Based Sample Selection for Label-Efficient Blind Image Quality Assessment”, IEEE Transactions on Circuits and Systems for Video Technology, 2024 (中科院一区Top，图像处理).

宋天舒，夏辉*，“基于数值稳定型神经网络的Villain-Lai-Das Sarma 方程的动力学标度行为研究”, 物理学报, 2024 (物理中文顶刊，SCI ).

Tianshu Song, Leida Li*, Jinjian Wu, Yuzhe Yang, Yaqian Li, Yandong Guo, and Guangming Shi, “Knowledge-Guided Blind Image Quality Assessment with Few Training Samples”, IEEE Transactions on Multimedia, 2023 (中科院一区Top，图像处理).

Tianshu Song, Leida Li*, Pengfei Chen, Hantao Liu, and Jiansheng Qian, “Blind Image Quality Assessment for Authentic Distortions by Intermediary Enhancement and Iterative Training”, IEEE Transactions on Circuits and Systems for Video Technology, 2022 (中科院一区Top，图像处理).

Leida Li, Tianshu Song*, Jinjian Wu, Weisheng Dong, Jiansheng Qian*, and Guangming Shi, “Blind Image Quality Index for Authentic Distortions with Local and Global Deep Feature Aggregation”, IEEE Transactions on Circuits and Systems for Video Technology, 2022 (中科院一区Top，图像处理).

Tianshu Song and Hui Xia*, “Extensive Numerical Simulations of Surface Growth with Temporally Correlated Noise”, Physical Review E, 2021 (JCR Q1，统计物理).

Tianshu Song and Hui Xia*, “Kinetic Roughening and Nontrivial Scaling in the Kardar–Parisi–Zhang Growth with Long-Range Temporal Correlations”, Journal of Statistical Mechanics: Theory and Experiment, 2021 (JCR Q1， 统计物理).

Tianshu Song and Hui Xia*, “Difference in the Dynamics of Logistic Maps”, International Journal of Modern Physics B, 2019 (JCR Q1，统计物理).

Tianshu Song and Hui Xia*, “Long-Range Temporal Correlations in the Kardar–Parisi–Zhang Growth: Numerical Simulations”, Journal of Statistical Mechanics: Theory and Experiment, 2016 (JCR Q1，统计物理).

宋天舒，程德强，寇旗旗，李雷达，陈亮亮，江鹤，“基于图像质量启发的盲图像去运动模糊算法”，2024-02-13，中国，ZL 202310985961.1 (已授权发明专利).

宋天舒，程德强，寇旗旗，李雷达，陈亮亮，江鹤，“基于主动学习的少样本无参考图像质量评价算法”，2024-01-26，中国，ZL 202311221440.5 (已授权发明专利).