Shuzhou Yang
Scholar

Shuzhou Yang

Google Scholar ID: y-gvXecAAAAJ
Peking University
Computer VisionMachine LearningGenerative Model
Citations & Impact
All-time
Citations
1,074
 
H-index
10
 
i10-index
10
 
Publications
15
 
Co-authors
7
list available
Resume (English only)
Academic Achievements
  • - Selected Publications: 'GenCompositor: Generative Video Compositing with Diffusion Transformer', '4DVD: Cascaded Dense-view Video Diffusion Model for High-quality 4D Content Generation', 'Hybrid Fourier Score Distillation for Efficient One Image to 3D Object Generation', 'Neural Video Fields Editing', 'DiffLLE: Diffusion-based Domain Calibration for Weak Supervised Low-light Image Enhancement', 'Implicit Neural Representation for Cooperative Low-light Image Enhancement', 'Multi-scale Synergism Ensemble Progressive and Contrastive Investigation for Image Restoration', 'NeRFocus: Neural Radiance Field for 3D Synthetic Defocus'
  • - Awards: Peking University May Fourth Scholarship (2025), Outstanding Student (2023 & 2025)
Research Experience
  • - Ph.D. Student at Peking University
  • - Involved in multiple research projects such as GenCompositor, 4DVD, etc.
Education
  • - Ph.D. Student in Computer Science at School of Electronic and Computer Engineering, Peking University, supervised by Prof. Jian Zhang (since 2022)
  • - B.Eng. in Software Engineering from Dalian University of Technology, worked closely with Prof. Risheng Liu and Prof. Xin Fan in the field of low-level vision (graduated 2022)
Background
  • Primary research interests include computer vision, diffusion model, and machine learning, mainly focusing on video-related AIGC, low-level vision, and novel view synthesis.
Miscellany
  • Served as a reviewer for multiple journals and conferences including TPAMI, IJCV, TIP, TMM, TCSVT, TOMM, JSTSP, CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, Siggraph, AAAI, etc. Teaching assistant for a computer vision course.