刘成旭，博士，西安交通大学助理教授，美国加州大学访问学者。于2025年和2019年分别获得西安交通大学博士和学士学位，曾赴微软亚洲研究院、旷视科技研究院长期交流学习。

    入选西安交通大学青年优秀人才计划A类、2025年西安交通大学"启航榜样"、2025年西安交通大学优秀毕业生、2024年首届中国科协青年人才托举工程博士生专项计划、2023年西安交通大学"学术之星"(每年10人)、2023年西安交通大学创新领军人才项目、2022年西安交通大学"优秀博士研究生标兵"(每年16人)、2022年微软"明日之星"等十余项荣誉；曾荣获博士研究生国家奖学金(2024、2022)、中国移动特等奖学金、华为奖学金、百度奖学金全球前20、全国研究生电子设计大赛最具商业价值奖、全国一等奖等二十余项奖励。中国计算机学会、中国图象图形学学会、IEEE会员，担任ICLR26领域主席，TPAMI、IJCV、TIP、CVPR、ICCV、ECCV、NeurIPS、ICLR、ICML等权威期刊会议审稿人。主要研究底层视觉重建、目标检测、模型轻量化结构设计与部署，以独立第一作者发表CVPR、ICCV等计算机视觉领域权威期刊会议文章十余篇、主持中央高校基本科研业务费1项。

[2025.09] I serve as ICLR 2026 Area Chair

2019.09~2025.06        西安交通大学    信息与通信工程        硕博连读 （Prof. 钱学明）

2024.01~2024.12    University of California, Merced      博士联合培养  （Prof. Ming-Hsuan Yang）

2015.09~2019.06          西安交通大学        信息工程                本科

[1] Chengxu Liu, Huan Yang, Jianlong Fu, Xueming Qian. Learning Trajectory-Aware Transformer for Video Super-Resolution[C]. CVPR. 2022: 5687-5696.(CCF-A，Oral Presentation).

[2] Chengxu Liu, Xuan Wang, Xiangyu Xu, Ruhao Tian, Shuai Li, Xueming Qian, Ming-Hsuan Yang. Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring[C]. CVPR. 2024: 25595-25605.(CCF-A).  

[3] Chengxu Liu, Lu Qi, Jinshan Pan, Xueming Qian, Ming-Hsuan Yang. Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing[C]. ICCV. 2025. (CCF-A).

[4] Chengxu Liu, Lu Qi, Jinshan Pan, Xueming Qian, Ming-Hsuan Yang. Learning Deblurring Texture Prior from Unpaired Data with Diffusion Model[C]. ICCV. 2025. (CCF-A).

[5] Chengxu Liu, Xuan Wang, Shuai Li, Yuzhi Wang, Xueming Qian. Frequency and Spatial Interactive Learning for Image Restoration in Under-Display Cameras[C]. ICCV. 2023: 12537-12546.(CCF-A).  

[6] Chengxu Liu, Huan Yang, Jianlong Fu, Xueming Qian. 4D LUT: Learnable Context-Aware 4D Lookup Table for Image Enhancement[J]. IEEE TIP, 2023, 32: 4742-4756.(CCF-A，IF=10.8).

[7] Chengxu Liu, Huan Yang, Jianlong Fu, Xueming Qian. TTVFI: Learning Trajectory-Aware Transformer for Video Frame Interpolation[J]. IEEE TIP, 2023, 32: 4728-4741.(CCF-A，IF=10.8).  

[8] Chengxu Liu, Xuan Wang, Yuanting Fan, Shuai Li, Xueming Qian. Decoupling Degradations with Recurrent Network for Video Restoration in Under-Display Camera[C]. AAAI. 2024, 38(4): 3558-3566.(CCF-A).

[9] Chengxu Liu, Zongyang Da, Yuanzhi Liang, Yao Xue, Guoshuai Zhao, Xueming Qian. Product Recognition for Unmanned Vending Machines[J]. IEEE TNNLS, 35(2): 1584-1597, 2022.(CCF-B，IF=10.4).

[10] Chengxu Liu, Yaru Zhang, Yao Xue, Xueming Qian. AJENet: Adaptive Joints Enhancement Network for Abnormal Behavior Detection in Office Scenario[J]. IEEE TCSVT, 34(3): 1427-1440, 2023.(CCF-B，IF=8.4).

[11] Chengxu Liu, Yuanzhi Liang, Yao Xue, Xueming Qian, Jianlong Fu. Food and Ingredient Joint Learning for Fine-Grained Recognition[J]. IEEE TCSVT, 31(6): 2480-2493, 2020.(CCF-B，IF=8.4).

[12] Chengxu Liu, Zongyang Da, Yuanzhi Liang, Yao Xue, Guoshuai Zhao, Xueming Qian. Split-Check: Boosting Product Recognition via Instance-Level Retrieval[J]. IEEE TII, 20(3): 3521-3529, 2023.(CCF-C，IF=12.3).

[13] Changlong Gao*, Chengxu Liu*, Yujie Dun, Xueming Qian. CSDA: Learning Category-Scale Joint Feature for Domain Adaptive Object Detection[C]. ICCV. 2023: 11421-11430.(共一，CCF-A).

[14] Yuanting Fan*, Chengxu Liu*, Nengzhong Yin, Changlong Gao, Xueming Qian. AdaDiffSR: Adaptive Region-aware Dynamic Acceleration Diffusion Model for Real-World Image Super-Resolution[C]. ECCV. 2024: 396-413.(共一，CCF-B).

[15] Nengzhong Yin*, Chengxu Liu*, Ruhao Tian, Xueming Qian. SDPDet: Learning Scale-Separated Dynamic Proposals for End-to-End Drone-View Detection[J]. IEEE TMM, 2024, 6: 7812-7822.(共一，CCF-B，IF=8.4).

[16] Yuanting Fan*, Chengxu Liu*, Ruhao Tian, Xueming Qian. InstanceSR: Efficient Reconstructing Small Object with Differential Instance-level Super-Resolution[J]. IEEE TCSVT, 35(3): 2740 - 2752, 2025.(共一，CCF-B，IF=8.4).

[17] Jinjin Qian*, Chengxu Liu*, Yubin Ai, Guoshuai Zhao, Xueming Qian. Enhancing Autonomous Vending Machine Product Recognition Through Depth-Guided Regression Refinement[J]. IEEE TII. 2025.(共一，CCF-C，IF=12.3). 

[18] Jinjin Qian*, Chengxu Liu*, Yubin Ai, Guoshuai Zhao, Xueming Qian. Rethinking Label Assignment and Sampling Strategies for Two-Stage Oriented Object Detection[J]. IEEE GRSL, 2025.(共一).

[19] Pengbo Guo, Chengxu Liu, Xingsong Hou, Xueming Qian. QueryCDR: Query-based Controllable Distortion Rectification Network for Fisheye Images[C]. ECCV. 2024: 266–284.(CCF-B).

[20] Pengbo Guo, Chengxu Liu, Xingsong Hou, Xueming Qian. Towards Better Distortion Feature Learning for Object Detection in Top-View Fisheye Cameras[J]. IEEE TCSVT.2024. (CCF-B，IF=8.4).

[21] Zhenni Yang, Chengxu Liu, Xueming Qian. SLE: Out-of-Distribution Detection with Shallow Layer-Driven Enhancement[J]. IEEE TMM. 2024.(CCF-B，IF=8.4).

[22] Xiaolong Guo, Chengxu Liu, Xueming Qian, Zhixiao Wang, Xubin Feng, Yao Xue. Single-Domain Generalized Object Detection with Frequency Whitening and Contrastive Learning[J]. IEEE TMM, 2025.(CCF-B，IF=8.4).