谢琦

   副教授，博导

   西安交通大学

   数学与统计学院

   西安 陕西 710049

   办公室： 数学楼 318

   邮箱： xie.qi@mail.xjtu.edu.cn

   Google Scholar：https://scholar.google.com/citations?hl=zh-CN&user=2ZqIzTMAAAAJ

工作经历

2022.02至今              西安交通大学       数学与统计学院      青拔B类副教授 (博后导师：孟德宇)

2020.12至2022.02     西安交通大学       数学与统计学院      青秀A类助理教授 (博后导师：孟德宇)

教育经历

2013.09至2020.12     西安交通大学       应用数学（博士）        导师：徐宗本

2017.09至2018.09     普林斯顿大学       统计学（访问学者）     导师：范剑青

2014.07至2014.09     香港理工大学       计算机（访问学生）     导师：张   磊

2009.09至2013.06     西安交通大学       理科数学实验班（本科） 

奖励荣誉

2022年 CCF优秀博士学位论文激励计划

2021年 ACM中国优博提名奖

2023年 陕西省优秀博士论文

2024年 华为火花奖

研究方向：机器学习与图像处理的基础方法、图像处理中的基础深度网络模块设计

在研课题：参数化卷积方法及其应用、模型驱动的深度学习方法、等变深度网络设计

欢迎具有良好数学基础、编程基础，有志于从事机器学习、计算机视觉与人工智能领域研究的同学报考硕士/博士研究生。请有报考意向学生提前通过邮件发送简历联系。

主要论文发表：

1. Xie Qi, Fu Jiahong, Xu Zongben, Meng Deyu*. Rotation Equivariant Arbitrary-scale Image Super-Resolution. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 2025. [code]

2. Pang Zhiqiang, Wang Hong, Xie Qi*, Meng Deyu, Xu Zongben. TRG-Net: An Interpretable and Controllable Rain Generator. IEEE Transactions on Neural Networks and Learning Systems, 2025.

3. Sun Zihong, Wang Hong, Xie Qi*, Zheng Yefeng,  Meng Deyu. RSF-Conv: Rotation-and-Scale Equivariant Fourier Parameterized Convolution for Retinal Vessel Segmentation. IEEE Transactions on Neural Networks and Learning Systems. 2025 

4. Liu Hanze, Fu Jiahong, Xie Qi*, Meng Deyu. Rotation-Equivariant Self-Supervised Method in Image Denoising, CVPR, 2025. [code]

5. Bai Yulu , Fu Jiahong, Xie Qi*, Meng Deyu. A Regularization-Guided Equivariant Approach for Image Restoration, CVPR, 2025. [code]

6. Tan Feiyu, Wang Yuhan, Xie Qi*, et al. DS-Net: A Model Driven Network Framework for Lesion Segmentation on Fundus Image[J]. Knowledge-Based Systems, 2025, 315: 113242.
7. Jiahong Fu, Xie Qi*, Meng Deyu, Xu Zongben. Rotation Equivariant Proximal Operator for Deep Unfolding Methods in Image Restoration IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 2024. 
8. Xie Qi, Zhao Qian, Xu Zongben, Meng Deyu. Fourier Series Expansion Based Filter Parametrization for Equivariant Convolutions. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 2023. [code]
9. Xie Qi, Zhou Minghao, Zhao Qian, Meng Deyu and Xu Zongben. MHF-Net: An interpretable deep network for multispectral and hyperspectral image fusion[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 2020, 44(3): 1457-1473. ( ESI高被引)
10. Xie Qi, Zhao Qian, Meng Deyu and Xu Zongben. Kronecker-basis-representation based tensor sparsity and its applications to tensor recovery[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 2018, 40(8):1888–1902. (ESI高被引)
11. Xie Qi, Zeng Dong, Zhao Qian, Meng Deyu, Xu Zongben, Liang Zhengrong and Ma Jianhua. Robust low-dose CT sinogram preprocessing via exploiting noise-generating mechanism[J]. IEEE Transactions on Medical Imaging (TMI). 2017, 36(12):2487–2498. 
12. Xie Qi, Zhao Qian, Meng Deyu, Xu Zongben, Gu Shuhang, Zuo Wangmeng and Zhang Lei. Multispectral images denoising by intrinsic tensor sparsity regularization[C]. CVPR, 2016: 1692–1700. 
13. Xie Qi, Zhou Minghao, Zhao Qian, Meng Deyu*, Wangmeng Zuo and Xu Zongben. Multispectral and hyperspectral image fusion by MS/HS fusion net[C]. CVPR, 2019: 1585–1594. 
14. Xie Qi, Zhao Qian, Xu Zongben and Meng Deyu*. Color and Direction-Invariant Nonlocal self-similarity prior and its application to color image denoising[J]. Science China-information Sciences. 
15. Gu Shuhang, Xie Qi, Meng Deyu, Zuo Wangmeng, Feng Xiangchu and Zhang Lei*. Weighted nuclearnorm minimization and its applications to low level vision[J]. International Journal of Computer Vision (IJCV). 2017, 121(2):183–208.(ESI高被引)
16. Zhou Man, Yan Keyu, Pan Jinshan, Xie Qi, et al. Memory-augmented deep unfolding network for guided image super-resolution[J]. International Journal of Computer Vision (IJCV), 2023, 131(1): 215-242.
17. Wang Hong#, Xie Qi#, Zhao Qian and Meng Deyu*. A Model-Driven Deep Neural Network for Single Image Rain Removal [C]. CVPR, 2020 
18. Peng Jiangjun#, Xie Qi#, Zhao Qian, Wang Yao, Leung Yee, and Meng Deyu*. Enhanced 3DTV regularization and its applications on HSI denoising and compressed sensing[J]. IEEE Transactions on Image Processing (TIP). 
19. Wang Hong, Wu Yichen, Xie Qi*, et al. Structural residual learning for single image rain removal[J]. Knowledge-Based Systems, 2021, 213: 106595.
20. Fu Jiahong, Wang Hong, Xie Qi*, Zhao Qiang, Meng Deyu, Xu Zongben. KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution[J]. ECCV, 2022
21. Wang Hong, Xie Qi*, Zhao Qian, Li Yuexiang, Liang Yong, Zheng Yefeng, Meng Deyu*；RCDNet: An Interpretable Rain Convolutional Dictionary Network for Single Image Deraining；IEEE Transactions on Neural Networks and Learning Systems 2022
22. Wang Hong, Xie Qi*, Li Yuexiang, et al. Orientation-Shared Convolution Representation for CT Metal Artifact Learning[C]. MICCAI, 2022: 665-675. 
23. Wang Hong, Xie Qi*, Zhao Qian, Li Yuexiang, Liang Yong, Zheng Yefeng, Meng Deyu. RCDNet: An Interpretable Rain Convolutional Dictionary Network for Single Image Deraining, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023
24. Wang Hong, Xie Qi, Zeng Dong, et al. OSCNet: Orientation-Shared Convolutional Network for CT Metal Artifact Learning[J]. IEEE Transactions on Medical Imaging, 2023. 
25. Liu Xinyi, Xie Qi, Zhao Qian, Wang Hong, Meng Deyu. Low-light image enhancement by retinex-based algorithm unrolling and adjustment[J]. IEEE Transactions on Neural Networks and Learning Systems, 2023. 
26. Wang Hong, Xie Qi，Wu Yichen, Zhao Qian and Meng Deyu. Single image rain streaks removal: a review and an exploration[J]. International Journal of Machine Learning and Cybernetics. 2020, 1–20. 
27. Zeng Dong, Xie Qi, Cao Wenfei, Lin Jiahui, Zhang Hao, Zhang Shanli, Huang Jing, Bian Zhaoying, Meng Deyu, Xu Zongben, et al. Low-dose dynamic cerebral perfusion computed tomography reconstructionvia kronecker-basis-representation tensor sparsity regularization[J]. IEEE Transactions on Medical Imaging (TMI). 2017, 36(12):2546–2556.
28. Shu Jun, Xie Qi, Yi Lixuan, Zhao Qian, Zhou Sanping, Xu Zongben and Meng Deyu*. Meta-weight-net: Learning an explicit mapping for sample weighting[C]. NeurIPS, 2019: 1917–1928.
29. Li Minghan, Xie Qi, Zhao Qian, Wei Wei, Gu Shuhang, Tao Jing and Meng Deyu*. Video rain streak removal by multiscale convolutional sparse coding[C]. CVPR, 2018: 6644–6653. 
30. Zeng Dong, Xie Qi, Bian Zhaoying, et al. Noise suppression for cerebral perfusion CT via intrinsic tensor sparsity regularization: Initial study[C], IEEE Nuclear Science Symposium, Medical Imaging Conference and Room-Temperature Semiconductor Detector Workshop(NSS/MIC/RTSD). 2016: 1-4.
31. Hu Zhengyang, Liu Guanzhang, Xie Qi, Xue Jiang, Deyu Meng, Deniz Gunduz. A learnable optimization and regularization approach to massive MIMO CSI feedback[J]. IEEE Transactions on Wireless Communications, 2023.
32. Gu Shuhang, Zuo Wangmeng, Xie Qi, Meng Deyu, Feng Xiangchu and Zhang Lei. Convolutional sparse coding for image super-resolution[C]. ICCV, 2015: 1823–1831. 
33. Ma Fan, Meng Deyu, Xie Qi, Li Zina and Dong Xuanyi. Self-paced co-training[C]// JMLR. org. Proceedings of the 34th International Conference on Machine Learning-Volume 70: JMLR. org, 2017: 2275–2284. 
34. Wei Wei, Yi Lixuan, Xie Qi, Zhao Qian, Meng Deyu* and Xu Zongben Should we encode rain streaks in video as deterministic or stochastic?[C]. ICCV, 2017: 2516–2525. 
35. Zhao Qian, Meng Deyu*, Kong Xu, Xie Qi, Cao Wenfei, Wang Yao and Xu Zongben. A novel sparsity measure for tensor recovery[C]. ICCV, 2015: 271–279. 
36. Zhao Qian, Meng Deyu*, Jiang Lu, Xie Qi, Xu Zongben, Hauptmann, Alexander G. Self-paced learning for matrix factorization[C]. Twenty-ninth AAAI conference on artificial intelligence, 2015. 
37. Zeng Dong, Lisha Yao, Ge Yongshuai, Li Sui, Xie Qi, Zhang Hao, et al. Full-Spectrum-Knowledge-Aware Tensor Model for Energy-Resolved CT Iterative Reconstruction[J]. IEEE Transactions on Medical Imaging (TMI), 2020.  
38. Sui Li, Zeng Dong, Peng Jiangjun, Bian Zhaoying, Zhang Hao, Xie Qi, Wang Yongbo, et al. An efficient iterative cerebral perfusion CT reconstruction via low-rank tensor decomposition with spatial–temporal total variation regularization[J]. IEEE Transactions on Medical Imaging (TMI), 2018, 38(2): 360-370. 
39. Meng Mingqiang, Li Sui, Yao Lisha, Li Danyang, Zhu Manman, Gao Qi, Xie Qi, Zhao Qian, Bian Zhaoying, Huang Jing, Meng Deyu, et al. Semi-supervised learned sinogram restoration network for low-dose CT image reconstruction[C], Medical Imaging 2020: Physics of Medical Imaging. International Society for Optics and Photonics, 2020, 11312: 113120B.

专著发表：

谢琦; 图像数据先验的数学建模及其应用, CCF优博丛书, 机械工业出版社, 2024 

专利发表：

1. 谢琦，孟德宇，马建华，赵谦，徐宗本. 一种低剂量X射线CT图像重建方法:中国, ZLCN201611002595.X [发明专利]. 2020-06 (已授权)
2. 谢琦, 孟德宇，周明皓，赵谦，徐宗本.一种基于深度学习和模型驱动的多高光谱图像融合方法 受理:中国, [发明专利]. (待授权)
3. 谢琦，庞智强，孟德宇，徐宗本.一种具有可解释性和可控性的雨生成方法, [发明专利]. (待授权)
4. 符佳宏，谢琦，孟德宇，徐宗本一种适用于CT深度学习重建的等变近端算子方法及装置, [发明专利]. (待授权)
5. 孟德宇，谢琦，赵谦，马建华，耿明瑞，邓芸. 一种无监督/半监督CT图像重建深度网络训练方法:中国, ZLCN201810798715.4 [发明专利]. 2020-05 (已授权)
6. 孟德宇，谢琦，赵谦，魏玮，易丽璇，徐宗本. 一种基于噪声建模的视频去雨方法:中国, ZLCN201710992669.7 [发明专利]. 2020-05 (已授权)
7. 孟德宇，彭江军，谢琦，赵谦，王尧. 一种基于E-3DTV正则的高光谱图像修复方法:中国, ZLCN201811046032.X [发明专利]. 2020-06 (已授权)
8. 谭菲宇，王雨菡，谢琦， 孟德宇. 一种基于旋转与放缩等变网络的眼底血管分割方法, [发明专利]. (待授权)
9. 孟德宇，谢琦，马凡，李梓娜，赵谦. 自步-协同训练学习方法:中国, [发明专利]. (待授权)
10. 孟德宇，李明晗，赵谦，谢琦. 一种基于多尺度卷积稀疏编码的视频去雨雪方法:中国, [发明专利]. (已授权)
11. 赵谦，刘心怡，谢琦，孟德宇，徐宗本. 一种RAW格式弱光图像增强方法及装置