Fei Shen (沈飞)

Research Fellow
National University of Singapore
School of Computing
NExT++ Research Center
Email: shenfei29_at_nus.edu.sg
Google Scholar • Github

About Me

Hi 😄! I am currently a Research Fellow at the NExT++ Center at the National University of Singapore (NUS). I actively collaborate with leading industry partners such as Tencent AI Lab, Huawei, AIUNI, GuijiAI, and Mobvoi, focusing on cutting-edge research in 2D/3D content generation. My research interests lie in human-centered, controllable, and consistent visual generation, including pose-guided person generation, virtual try-on, and long-term talking face synthesis, particularly in the context of e-commerce applications. Motivated by the vision of achieving digital immortality and machine consciousness, I am dedicated to pushing the boundaries of generative AI. Prior to my current position, I was an avid algorithm competition enthusiast, securing over 50 top-three finishes, including five championships in CCF A-class workshop challenges. I am a strong advocate of sharing🌱, collaborating🤝, advancing🚀, and innovating💡. Passionate about bridging fundamental research with real-world impact, I strive to ensure my work contributes to both academic progress and practical value. I am also actively seeking industrial collaborations and exploring potential entrepreneurial opportunities. If you’re interested in collaborating or would like to connect, feel free to reach out via email! 😊

NEWS!

Research Experience

  National University of Singapore, Singapore (Apr 2025 - Present)
  National University of Singapore, Singapore (May 2024 - Mar 2025)
  Tencent Inc., Shenzhen China (May 2023 - May 2024)
  Nanjing University of Science and Technology, Nanjing China (Sep 2021 - Mar 2025)
Selected Publications
Preprints
StyleTailor: Towards Personalized Fashion Styling via Hierarchical Negative Feedback
H. Ma, F. Shen, H. Xu, X. Wang, G. Xu, J. Zheng, L. Qu, M. Li
arXiv 2025 [PDF] [Code]
TL;DR: An Agent for personalized fashion styling.
CharacterShot: Controllable and Consistent 4D Character Animation
J. Gao, J. Li, W. Liu, Y. Zeng, F. Shen, K. Chen, Y. Sun, C. Zhao
arXiv 2025 [PDF] [Code]
TL;DR: Controllable and consistent 4D character animation framework.
Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization
C. Wang, Z. Deng, Z. Jiang, F. Shen, Y. Yin, S. Gan, Z. Cheng, S. Ge, Q. Gu
arXiv 2025 [PDF] [Code]
TL;DR: Controllable sign language video generation.
Fine-grained Image Retrieval via Dual-Vision Adaptation
X. Jiang, M. Cao, H. Tang, F. Shen, Z. Li
arXiv 2025 [PDF] [Code]
TL;DR: A dual-branch adaptation framework for fine-grained image retrieval.
IMAGHarmony: Controllable Image Editing with Consistent Object Quantity and Layout
F. Shen, X. Du, Y. Gao, J. Yu, Y. Cao, X. Lei, J. Tang
arXiv 2025 [PDF] [Code]
TL;DR: Controllable image editing with consistent object quantity and layout.
IMAGGarment-1: Fine-Grained Garment Generation for Controllable Fashion Design
F. Shen, J. Yu, C. Wang, X. Jiang, X. Du, J. Tang
arXiv 2025 [PDF] [Code]
TL;DR: Controllable fashion design.
V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation
C. Wang, K. Tian, J. Zhang, Y. Guan, F. Luo, F. Shen, Z. Jiang, Q. Gu, X. Han, W. Yang
arXiv 2024 [PDF] [Code]
TL;DR: Explores strong and weak conditional relationships for portrait video generation.
2025
UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation
Q. Guo, A. Zeng, D. Yue, C. Yang, Y. Cao, H. Guo, F. Shen, W. Liu, X. Liu, D. Xu
ICML [PDF] [Code]
TL;DR: Proposes a unified diffusion transformer for keypoint-guided multi-class image generation.
Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model
F. Shen, C. Wang, J. Gao, Q. Guo, J. Dang, J. Tang, T.-S. Chua
ICML [PDF] [Code]
TL;DR: Multilingual long-term talkingface.
FaceShot: Bring Any Character into Life
J. Gao, Y. Sun, F. Shen, X. Jiang, Z. Xing, K. Chen, C. Zhao
ICLR [PDF] [Code]
TL;DR: Talkingface plugin for any character.
Ensembling Diffusion Models via Adaptive Feature Aggregation
C. Wang, K. Tian, Y. Guan, F. Shen, Z. Jiang, Q. Gu, J. Zhang
ICLR [PDF] [Code]
TL;DR: Uses routing aggregation for ensembling multiple diffusion models.
2024
IMAGDressing-v1: Customizable Virtual Dressing
F. Shen, X. Jiang, X. He, H. Ye, C. Wang, X. Du, Z. Li, J. Tang
AAAI [PDF] [Code]
TL;DR: Proposes the virtual dressing task and introduces a new dataset.
Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models
F. Shen, H. Ye, S. Liu, J. Zhang, C. Wang, X. Han, W. Yang
AAAI [PDF] [Code]
TL;DR: Proposes non-autoregressive diffusion models for story generation.
MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-view Stereo
Z. Yuan, C. Liu, F. Shen, Z. Li, J. Luo, T. Mao, Z. Wang
AAAI
DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-view Stereo
Z. Yuan, J. Luo, F. Shen, Z. Li, C. Liu, T. Mao, Z. Wang
AAAI
Exploring the Potential of Large Vision-Language Models for Unsupervised Text-Based Person Retrieval
Z. Li, J. Li, Y. Shi, J. Chen, S. Huang, L. Tu, F. Shen, H. Ling
AAAI
IMAGPose: A Unified Conditional Framework for Pose-Guided Person Generation
F. Shen, J. Tang
NeurIPS [PDF] [Code]
TL;DR: Unifies person generation under diverse conditions.
Triplet Contrastive Representation Learning for Unsupervised Vehicle Re-identification
F. Shen, X. Du, L. Zhang, X. Shu, J. Tang
ACM Transactions on Multimedia Computing, Communications and Applications
Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models
F. Shen, H. Ye, J. Zhang, C. Wang, X. Han, W. Yang
ICLR [PDF] [Code]
TL;DR: Introduces concat/inpainting methods for generation.
Before 2024
GiT: Graph Interactive Transformer for Vehicle Re-identification
F. Shen, Y. Xie, J. Zhu, X. Zhu, H. Zeng
IEEE Transactions on Image Processing
An Efficient Multiresolution Network for Vehicle Re-identification
F. Shen, J. Zhu, X. Zhu, J. Huang, H. Zeng, Z. Lei, C. Cai
IEEE Internet of Things Journal
Exploring Spatial Significance via Hybrid Pyramidal Graph Network for Vehicle Re-identification
F. Shen, J. Zhu, X. Zhu, Y. Xie, J. Huang
IEEE Transactions on Intelligent Transportation Systems
Pedestrian-specific Bipartite-aware Similarity Learning for Text-based Person Retrieval
F. Shen, X. Shu, X. Du, J. Tang
ACM Multimedia
All Awards
Selected Awards
2023
IJCAI 2023 Workshop Challenge, Track II：Rotated Detection, Runner-up
Organizer: IJCAI
2022-2023“航天宏图杯”遥感影像智能处理算法大赛-遥感影像语义分割,一等奖
主办单位：国家自然科学基金委员会信息科学部
2023国际大数据产业博览会-生活垃圾检测,二等奖
主办单位：贵阳大数据交易所
2023IEEE IGRSS Data Fusion Contest Track 1, 3rd place
Organizer: IEEE IGRSS
2022
2022科大讯飞1024挑战赛,2个冠军;1个亚军;1个季军
基于可见光图像的柑橘花果梢识别挑战赛, 第一名
辣椒病虫害图像识别挑战赛, 第一名
智能硬件语音控制的时频图分类挑战赛 2.0, 第二名
基于小样本的异常检测任务挑战赛, 第三名
主办单位：科大讯飞
2022 全国大学生物联网设计竞赛,一等奖
主办单位：全国高等学校计算机教育研究会
2022 kaggle 微生物目标检测,第一名
主办单位：kaggle
2022华为digix全球校园精英挑战赛-车道线渲染检测,亚军, [Code]
主办单位：江苏省人工智能学会, 华为技术有限公司
2022 few-shot logo detection challenge of ICME workshop, 2nd place
Organizer: IEEE ICME
2022首届“兴智杯”全国人工智能创新应用大赛, 三等奖
主办单位：全国人工智能大会
2022船海数据应用创新大赛-海上目标检测, 三等奖
主办单位：中国船舶集团, 深海科学技术太湖实验室
2022 IEEE UV “Vision Meets Algae” Object Detection Challenge, 3rd place
Organizer: IEEE UV
2022 pet biometric Challenge of CVPR workshop, 3rd place, [Code]
Organizer：CVPR
Before 2022
2021华为云“东吴杯”数字转型创新大赛-汽车零部件检测,一等奖
主办单位：苏州市政府, 华为技术有限公司
2021海洋目标智能感知国际挑战赛-可见光目标检测,一等奖
主办单位：中国造船工程学会, 国际船舶与海洋工程创新与合作联盟(ICNAME), 中国图象图形学学会
2021福建省软件设计大赛,一等奖
主办单位：福建省工业和信息化厅
2021科大讯飞1024挑战赛,3个冠军;1个亚军
柑橘病虫害识别挑战赛, 第一名
遥感影像典型目标提取挑战赛, 第一名
农作物生长情况识别挑战赛, 第一名
叶菜病虫害图像识别挑战赛, 第二名
主办单位：科大讯飞
2021全国高校新星挑战赛-企业出题,揭榜挂帅, 双赛道一等奖
星宸科技轻量化人脸检测第一名
亿联科技室内行人跟踪第一名
主办单位：厦门工业和信息化局
2021“易华录”杯图像描述生成, 第二名
主办单位：天津工业和信息化局, 北京易华录信息技术股份有限公司
2021中国软件杯-软件设计大赛, 二等奖, [Code]
主办单位：工业和信息化部
2021全国人工智能创新(AIAC)应用大赛-钢铁瑕疵检测, 二等奖
主办单位：中国人工智能学会
2021全国数字生态创新大赛-智能算法赛, 第三名
主办单位：天池
WAIC世界人工智能大会-算法扩展挑战赛, 季军
主办单位: WAIC
2021“昇腾杯”遥感影像智能处理算法大赛-细粒度语义分割, 三等奖
主办单位：国家自然科学基金委员会信息科学部
2021海洋目标智能感知国际挑战赛-红外目标检测, 三等奖
主办单位：中国造船工程学会, 国际船舶与海洋工程创新与合作联盟(ICNAME), 中国图象图形学学会
2022 全国水下光学目标检测智能算法赛, 入围奖
主办单位：国家自然科学基金委员会信息科学部
2020 Visual Inductive Priors for Data-Efficient Computer Vision Object Detection, 1st place, [Code]
Organizer: ECCV
2020中国软件杯-软件设计大赛, 一等奖, [Code]
主办单位：工业和信息化部
2020 易华录不定向算法赛, 二等奖
主办单位：天津工业和信息化局, 北京易华录信息技术股份有限公司
2020 华为digix全球校园精英挑战赛-数码检索,第四名，[Code]
主办单位：江苏省人工智能学会, 华为技术有限公司
2020“中兴捧月”算法大赛-多目标跟踪, 优胜奖, [Code]
主办单位：中兴通讯股份有限公司
2020 “华为杯”第二届中国研究生人工智能创新应用大赛-小样本分类, 三等奖
主办单位：中国学位与研究生教育协会

Honors

  • Youth Talents Support Project, Doctoral Student Special Program (首届中国科协青年人才托举-博士生专项)
  • Outstanding Scholarship of the 2024 Tencent Rhino-bird Research Elite Program, Tencent, 2024
  • President's Medal, Nanjing University of Science and Technology, 2023
  • Graduate National Scholarship, Ministry of Education of China, 2021, 2023
  • Recipient of the National Scholarship for Study Abroad Program, China Scholarship Council, 2023
  • Huawei Developer Ecosystem Special Contribution Award, Huawei Developer Conference, 2023
  • Selected for Tencent Rhino-bird Elite Talent Program, Tencent, 2023
  • Kaggle Master, Kaggle, 2022

Professional Services

  • Journal Reviewer:
      • T-PAMI | T-IP | T-ITS | T-MM | T-VT | T-NNLS | T-AI | T-CSVT | IOTJ | NCA | NC
  • Conference Reviewer / Program Committee Member:
      • NeurIPS | ICLR | ICML | CVPR | ECCV | ICCV | IJCAI | MICCAI | ACM MM | ICME

Others

    In my free time, I enjoy activities such as running, playing soccer, and basketball. Additionally, I have undergone brief professional training in table tennis.