About Me

Hi, I am Zhifeng Wang (汪智峰), a third-year master's student at the College of Computer Science and Technology, National University of Defense Technology, advised by Prof. Kai Xu and Assoc. Prof. Renjiao Yi.

My research focuses on AI for healthcare, emphasizing structure-aware methods for image generation, reconstruction, and enhancement . By integrating anatomical priors and explicit structural constraints, I aim to improve the reliability and clinical relevance of learned representations. I am particularly interested in approaches translatable to real-world clinical workflows. In parallel, I explore physics-informed intelligence to better align learning-based models with underlying physical and imaging principles .

Email: zhifengwang@nudt.edu.cn / zhifengwang686@gmail.com

Open to research-oriented collaborations in AI for Healthcare, and other areas of computer vision. </div>

Current Focus

🧬 Structure-aware Medical Imaging 🔬 Medical Image Reconstruction & Enhancement Generative Modeling 📊 Clinical Visualization & Analysis ⚛️ Physics-informed Intelligence
</div>
As a result of this honesty, we are forced to doubt. — Richard Feynman
</div>

🛠 Tools & Projects

🔥 News

  • 2026.01: 🎉 One paper is accepted by ICASSP 2026,Congratulations to Lubing.
  • 2025.11: 🎉 Awarded the China National Scholarship (Ranking 3/183).
  • 2025.05: 🎉 One paper is accepted by TVC Journal.
  • 2025.04: 🎉 Won 1st place in the CVPR2025W "Mobile AI 2025 Real-Time Rendering Realistic Bokeh Challenge",Congratulations to Kang.
  • 2025.04: 🎉 Won 6th place in the CVPR2025W "Mobile AI Challenge: RGB Photo Enhancement on Mobile GPUs",Congratulations to Runhua.
  • 2025.02: 🎉 One paper is accepted by CVPR 2025 (CCF-A).
+ More

📝 Publications

Preprint 2026
PhysConSR teaser
PhysConSR: Learning Fast Differentiable Physically-Informed Continuous Medical Super-Resolution via 2D Gaussians
Zhifeng Wang, Long Peng, Xingyue Zhao, Chenyang Zhu, Kai Xu, Renjiao Yi.
  • Under Review, 2026.
Preprint 2025
Science Advances teaser
Time-indexed reuse of physical states for hardware-efficient in-sensor visual computing
Xiong, J., Huang, M., Zhifeng Wang, et al.
  • Science Advances, Under Review, 2025.
Preprint 2025
BoVAR teaser
BoVAR: Learning Adaptive Routing and Hierarchical Attention for Variable-Aperture Bokeh Rendering
Kang Chen, Shijun Yan, Zhifeng Wang, Aiwen Jiang.
  • Under Review, 2025.
CVPR 2025
VasTSD teaser
VasTSD: Learning 3D Vascular Tree-state Space Diffusion Model for Angiography Synthesis
Zhifeng Wang, Renjiao Yi, Xin Wen, Chenyang Zhu✉, Kai Xu✉
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
TVC 2025
Angio-Diff teaser
Angio-Diff: Learning a Self-Supervised Adversarial Diffusion Model for Angiographic Geometry Generation
Zhifeng Wang, Renjiao Yi✉, Xin Wen, Chenyang Zhu, Kai Xu, Kunlun He✉
  • The Visual Computer, 2025.
Meta-Radiology 2024
Survey teaser
Cardiovascular medical image and analysis based on 3D vision: A comprehensive survey
Zhifeng Wang, Renjiao Yi✉, Xin Wen, Chenyang Zhu, Kai Xu
  • Meta-Radiology, 2024.
PRCV 2022
PRCV teaser
JVCIR 2022
JVCIR teaser
Self-supervised multi-scale pyramid fusion networks for realistic bokeh effect rendering
Zhifeng Wang, Aiwen Jiang✉, Chunjie Zhang, Hanxi Li, Bo Liu
  • Journal of Visual Communication and Image Representation (JVCIR), 2022.

🎖 Honors and Awards

CVPRW 2025
MAI 2025 Bokeh Winner Certificate
Mobile AI Workshop and Challenges 2025
Organized by CVPR2025
  • MAI 2025 Bokeh Effect Rendering Challenge.
  • Winner.
  • 2025.11 China National Scholarship (3/183), 2025.
  • 2022.11 China National Scholarship (Top 0.2%), 2022.
  • 2022.09 First-class Academic Scholarship, 2022.
  • 2021.09 First-class Academic Scholarship, 2021.
  • 2020.09 First-class Academic Scholarship, 2020.

📖 Services

  • Reviewers: PRCV’23/24, CAD/CG, JVCIR, PG.
  • Memberships: IEEE Student Member, CSIG Student Member, CAAI Student Member, CVF Member.

💻 Internships


I know I am not the perfect one, yet aspire to chase the world and achieve greatness @ Zhifeng Wang — Latest update: 2026-04-23