- 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.