Xiaoyang Lyu
Scholar

Xiaoyang Lyu

Google Scholar ID: SF7bq48AAAAJ
The University of Hong Kong; Zhejiang University
Computer visionDepth Estimation
Citations & Impact
All-time
Citations
1,174
 
H-index
14
 
i10-index
16
 
Publications
20
 
Co-authors
15
list available
Resume (English only)
Academic Achievements
  • - Paper 'Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interaction' selected as a highlight poster (acceptance rate 2.8%) for CVPR 2024
  • - Paper 'EscherNet: A Generative Model for Scalable View Synthesis' chosen for an oral presentation (acceptance rate 0.78%) for CVPR 2024
  • - Three papers accepted to CVPR 2024, one as the first author
  • - Released code and demos about EscherNet, a multi-view conditioned diffusion model for generative view synthesis
  • - Released demos about SC-GS, a controllable dynamic Gaussian method
  • - Three papers accepted to ICCV 2023, one as the first author
  • - One paper accepted to CVPR 2023
  • - One paper accepted to ICRA 2023
Research Experience
  • No specific work experience or research project information provided.
Education
  • - PhD: CVMI lab at the University of Hong Kong, supervised by Xiaojuan Qi
  • - Master's degree: College of Control Science and Engineering at Zhejiang University, supervised by Prof. Yong Liu
  • - Bachelor's degree: Harbin Institute of Technology
Background
  • Research Interests: Computer vision and robotics. Current focus is on 3D scene reconstruction, including neural rendering and depth estimation. Aspires to develop a simulator capable of seamlessly transposing real-world environments into the virtual realm, to expedite the integration of robotics, augmented reality (AR), and virtual reality (VR) applications.
Miscellany
  • Contact: Email / Google Scholar / Github