I am a Ph.D. student at the Australian National University, supervised by Prof. Hongdong Li, Dr. Chuong Nguyen and Prof. Kaihao Zhang. My research focuses on 3D Computer Vision, 3D Reconstruction, and Neural Rendering. I received my Master’s degree in Optical Engineering from Zhejiang University supervised by Prof. Sailing He.
A two-stage framework for human-object interaction video reenactment that queries a 3D foundation model over multi-view references to generate 3D-aware object priors for DiT-based video generation.
Novel approach combining deformable Gaussian splatting and dynamic neural surfaces for monocular dynamic 3D reconstruction.
Novel approach for reconstructing reflective objects using geometrically supervised 2D Gaussian Splatting.
A method to enhance multi-view consistency for improved 3D scene reconstruction.
Novel technique for reconstructing objects inside transparent containers using neural networks.
VFA, a voxelized 3D feature aggregation method, improves multiview detection accuracy by reducing occlusion and projection errors.