👋 Hi, I am Zhenghong Zhou(周政宏), an incoming Ph.D. student in the Department of Computer Science, University of Rochester, supervised by Prof. Jiebo Luo. I completed my M.S. and B.E. degree at Huazhong University of Science and Technology (HUST), supervised by Prof. Xinggang Wang and Prof. Wenyu Liu.

I am interested in 3D vision, multi-modal models and specific applications such as medicine.

• 3D vision: Generate, reconstruct, and understand the real 3D world with minimal required information.
• Multi-modal models: Leveraging text, images, and other modalities to enhance the intelligence of the model.
• Specific applications: 3D medical reconstruction, robotics, AR/VR.

Publications and Preprints

* indicates equal contribution.

• TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance
  Kan Wu*, Houwen Peng*, Zhenghong Zhou*, Bin Xiao, Mengchen Liu, Lu Yuan, Hong Xuan, Michael Valenzuela, Xi (Stephen) Chen, Xinggang Wang, Hongyang Chao, Han Hu
  ICCV, 2023
  paper, code

  

• TiAVox: Time-aware Attenuation Voxels for Sparse-view 4D DSA Reconstruction
  Zhenghong Zhou*, Huangxuan Zhao*, Jiemin Fang, Dongqiao Xiang, Lei Chen, Lingxia Wu, Feihong Wu, Wenyu Liu, Chuansheng Zheng, Xinggang Wang
  Preprint, 2023
  paper

  

• Self-supervised Learning Enables Excellent 3d Digital Subtraction Angiography Reconstruction from Ultra-sparse 2d Projection
  Huangxuan Zhao*, Zhenghong Zhou*, Feihong Wu*, Dongqiao Xiang*, Hui Zhao, Wei Zhang, Lin Li, Zhong Li, Jia Huang, Hongyao Hu, Chengbo Liu, Tao Wang, Wenyu Liu, Jinqiang Ma, Fan Yang, Xinggang Wang, Chuansheng Zheng
  Cell Reports Medicine, 2022
  paper, code

  

Internship

• Microsoft Research Asia, Beijing, China. Dec,2022-Jun,2023
  Research intern, mentored by Dr. Houwen Peng, working on visual-language models

Miscellaneous

Love badmintion, swim, reading, anime

Art is an explosion!

— Deidara