高 飞 Fei Gao

个人简介 Biography

高飞，西安电子科技大学杭州研究院，副研究员、湘湖菁英教授，入选浙江省万人计划青年科技人才。2015年获西安电子科技大学博士学位，曾于澳大利亚悉尼科技大学进行博士联合培养。长期从事计算机视觉研究，在 IEEE TNNLS、TIP、CVPR、ICCV、ACM MM、ICRA 等期刊/会议发表论文50余篇。主持国家自然科学基金面上/青年项目等纵向课题，获陕西省科学技术奖一等奖、IEEE ICME’21最佳展示奖亚军、全国博士后创新创业大赛铜奖等。

Fei Gao is currently an Xianghu Elite Professor at the Hangzhou Institute of Technology, Xidian University. He received his Ph.D. degree from Xidian University in 2015, and was a joint Ph.D. candidate at the University of Technology Sydney (UTS), Australia. His research focuses on computer vision, with over 50 publications in prestigious journals and conferences including IEEE TNNLS, TIP, CVPR, ICCV, ACM MM, and ICRA. He has led multiple research projects including the National Natural Science Foundation of China, and has received the First Prize of the Shaanxi Provincial Science and Technology Award and the Runner-up of the IEEE ICME’21 Best Demo Award.

研究兴趣 Research Interests

• 🎨 视觉内容生成：跨域图像合成、艺术风格迁移、图像修复/超分、文字生成
• 🛡️ 鲁棒视觉分析：质量评价、图像分类、目标检测、语义分割、跨域分析
• 🏥 医疗影像分析：肺癌、乳腺癌、眼底图像、脑血管、脑瘤等
• 🤖 具身智能：绘画/四足/人形机器人（VLM / VLA技术）

🧑‍🎓 招生信息 Prospective Students

团队每年招收 3-6 名硕士（通信工程 / 计算机技术），欢迎保研/考研同学申报！

将个人简历 + 成绩单整合为 1个PDF，命名为 姓名-学校.pdf，发送至邮箱（请查阅主页）。

• 品行良好 —— 正直、踏实、有团队精神
• 主动性强 —— 自学过深度学习/AI，能读论文、跑实验
• 动手能力 —— 在软/硬件方面有较好实践能力

代表性论文 Selected Publications

2026

• OOTD Derui Zhang, Yiji Feng, Fei Gao*, Nannan Wang. One is Enough: Disentangled Style Transfer via One-to-One Token Distillation. ACM MM, 2026.

• MAIST Hanyu Xing, Fei Gao*, Xi Yang, Ziyun Li, Pengyu Chen, Nannan Wang. Imagine A Reference: MLLM-Augmented Versatile Image Stylization. ACM MM, 2026.

• CPSP Qian Xu, Xi Li, Fei Gao, Qiming Zhang, Mingjin Zhang. CPSP: Channel Polarization and Global-Budget Structured Pruning for Infrared Small Target Detection. ACM MM, 2026.

• RidgeField-Net Mingjin Zhang, Shuaipeng Fan, Fei Gao, Jie Guo, Yunsong Li. RidgeField-Net: Continuous Spatio-Temporal Tube Fields for Tiny UAV Detection in Event Streams. ACM MM, 2026.

• ThermalDiffusion Mingjin Zhang, FengQin Lu, Jingyuan Gao, Fei Gao, Qiming Zhang. ThermalDiffusion: Confidence-Aware Diffusion for Sparse-View Thermal Infrared Novel View Synthesis. ACM MM, 2026.

• HiSAC Jiangpeng Wang, Fei Gao*, Nannan Wang. Hierarchical Style Aggregation for Versatile Chinese Handwriting Generation. ECCV, 2026.

• AdaNoise Xi Yang, Haoyuan Shi, Fei Gao*, Nannan Wang. AdaNoise: Cycle-Consistent Image Translation with Domain-Adaptive Noise Perturbation. IEEE TCSVT, 2026.

• KPE Ziyun Li, Huancheng Hu, Soon Hoe Lim, Xuyu Li, Fei Gao, Enmao Diao, Zezhen Ding, Michalis Vazirgiannis, Henrik Boström. A Kinetic Energy Perspective of Flow Matching. ICML (spotlight), 2026.

• PSMix Xin Wei, Qin Yang, Hongji Zhao, Fei Gao, Mingrui Zhu, Nannan Wang, Xinbo Gao. PSMix: Robust Point Cloud Recognition through Spectral Domain Mixing. ICML, 2026.

2025

• S3OIL Xi Yang, Haoyuan Shi, Ziyun Li, Maoying Qiao, Fei Gao*, Nannan Wang. S3OIL: Semi-Supervised SAR-to-Optical Image Translation via Multi-Scale and Cross-Set Matching. IEEE TIP, 6641-6654, Oct. 2025.

• KAN Policy Zikang Chen, Fei Gao, Ziya Yu, Peng Li. KAN Policy: Learning Efficient and Smooth Robotic Trajectories via Kolmogorov-Arnold Networks. IEEE RAL, 11164-11171, Sep. 2025.

• CADQ Yongjie Hu, Yifan Jiang, Ziyun Li, Fei Gao*, Henrik Boström, Nannan Wang. CADQ: Attribute-Consistent Face Cartoonization with Cross-modal Aligned and Deformable Quantization. ACM MM, 10681-10689, Oct. 2025.

• Q-Norm Lanning Zhang, Ying Zhou, Fei Gao*, Ziyun Li, Maoying Qiao, Jinlan Xu, Nannan Wang*. Q-Norm: Robust Representation Learning via Quality-Adaptive Normalization. ICCV, 13901-13911, Oct. 2025.

• SAIST Mingjin Zhang, Xiaolong Li, Fei Gao, Jie Guo, Xinbo Gao, Jing Zhang. SAIST: Segment Any Infrared Small Target Model Guided by Contrastive Language-Image Pre-training. CVPR, 9549-9558, 2025.

• QuARF Fei Gao, Ying Zhou, Ziyun Li, Wenwang Han, Jiaqi Shi, Maoying Qiao, Jinlan Xu, Nannan Wang*. QuARF: Quality-Adaptive Receptive Fields for Degraded Image Perception. AAAI, 39(16): 16708-16716, 2025.

• S3D Mingjin Zhang, Wenteng Shang, Fei Gao*, Qiming Zhang, FengQin Lu, Jing Zhang. Semi-supervised Infrared Small Target Detection with Thermodynamic-Inspired Uneven Perturbation and Confidence Adaptation. AAAI, 39(10): 10013-10021, 2025.

• MOCID Mingjin Zhang, Yuanjun Ouyang, Fei Gao, Jie Guo, Qiming Zhang*, Jing Zhang. MOCID: Motion Context and Displacement Information Learning for Moving Infrared Small Target Detection. AAAI, 39(10): 10022-10030, 2025.

• IRMamba Mingjin Zhang, Xiaolong Li, Fei Gao, Jie Guo. IRMamba: Pixel Difference Mamba with Layer Restoration for Infrared Small Target Detection. AAAI, 39(9): 10003-10011, 2025.

2024

• AesMamba Fei Gao, Yuhao Lin, Jiaqi Shi, Maoying Qiao, Nannan Wang*. AesMamba: Universal Image Aesthetic Assessment with State Space Models. ACM MM (Oral), 7444-7453, 2024.

• HMEG-SG Yu Chen, Fei Gao*, Yanguang Zhang, Maoying Qiao, Nannan Wang*. Generating Handwritten Mathematical Expressions From Symbol Graphs: An End-to-End Pipeline. CVPR, 15675-15685, June 2024.

• MDVPose Renshu Gu, Jiajun Zhu, Yixuan Si, Fei Gao, Jiamin Xu, Gang Xu. 3D Human Pose Estimation from Multiple Dynamic Views via Single-view Pretraining with Procrustes Alignment. ACM MM, 10363-10372, 2024.

• Fan Gong, Jialiang Chen, Jiajun Zhu, Qijian Bao, Fei Gao, Renshu Gu, Gang Xu. Micro-Action Recognition via Hierarchical Fusion and Inference. （Micro-Action Recognition Challenge, Global 4th Place）, ACM MM, 11327-11332, 2024.

• HIDA Fei Gao, Yifan Zhu, Chang Jiang, Nannan Wang. Human-Inspired Facial Sketch Synthesis with Dynamic Adaptation. ICCV, 7237-7247, 2023.

• HIRCA Fei Gao, Lingna Dai, Jingjie Zhu, Mei Du, Yiyuan Zhang, Maoying Qiao, Chenghao Xia, Nannan Wang, Peng Li*. Human-Robot Interactive Creation of Artistic Portrait Drawings. ICRA, 11297-11304, May 2024.

2023 and Before

• SAGE Biao Ma, Fei Gao*, Chang Jiang, Nannan Wang, Gang Xu. Semantic-aware Generation of Multi-view Portrait Drawings. IJCAI, 1258-1266, 2023.

• MATEIT Chang Jiang, Fei Gao*, Biao Ma, Yuhao Lin, Nannan Wang, Gang Xu. Masked and Adaptive Transformer for Exemplar Based Image Translation. CVPR, 22418-22427, 2023.

• CHAN Fei Gao, Xingxin Xu, Jun Yu, Meimei Shang, Xiang Li, Dacheng Tao. Complementary, Heterogeneous and Adversarial Networks for Image-to-Image Translation. IEEE TIP, 30: 3487-3498, 2021.

• CA-GAN Jun Yu, Xingxin Xu, Fei Gao*, Shengjie Shi, et al. Towards Realistic Face Photo-Sketch Synthesis via Composition-Aided GANs. IEEE TCYB, 51(9): 4350-4362, 2021.

• NAS-Lung Hanliang Jiang, Fuhao Shen, Fei Gao*, Weidong Han. Learning Efficient, Explainable and Discriminative Representations for Pulmonary Nodules Classification. PR, 113: 107825, 2021.

• iSkecher Fei Gao, Jingjie Zhu, Zeyuan Yu, Peng Li, Tao Wang. Making Robots Draw A Vivid Portrait In Two Minutes. IROS, 9585-9591, 2020.

• ReLIC Lin Zhao, Meimei Shang, Fei Gao*, et al. Representation Learning of Image Composition for Aesthetic Prediction. CVIU, 199: 103024, Oct. 2020.

• BLINDER Fei Gao, Jun Yu, Suguo Zhu, Qingming Huang, Qi Tian. Blind Image Quality Prediction by Exploiting Multi-level Deep Representations. PR, 81:432-442, Sep. 2018.

• RankIQA Fei Gao, Dacheng Tao, Xinbo Gao, Xuelong Li. Learning to rank for blind image quality assessment. IEEE TNNLS, 26(10): 2275-2290, Oct. 2015.

• NSS-MKL Xinbo Gao, Fei Gao, Dacheng Tao, Xuelong Li. Universal blind image quality assessment metrics via natural scene statistics and multiple kernel learning. IEEE TNNLS, 24(12): 2013-2026, 2013.