Paper 'Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting' accepted by NeurIPS 2025; 'Eventvad: Training-free event-aware video anomaly detection' accepted by ACM MM 2025; 'GM-MoE: Low-Light Enhancement with Gated-Mechanism Mixture-of-Experts' accepted by ICCV 2025; 'Learning-Based 3D Reconstruction Methods for Non-Collaborative Surfaces—A Metrological Evaluation' accepted by Metrology and selected as the cover paper; 'AccidentBlip: Agent of Accident Warning based on MA-former' accepted by IEEE IV 2025; 'In-Context Meta LoRA Generation' accepted by IJCAI 2025; 'RenderWorld' accepted by ICRA 2025; 'NeRFBK' accepted by GeoBench 2023 and the dataset is released.
Research Experience
Visiting CRCV at the University of Central Florida from June to December 2025, supervised by Prof. Mubarak Shah; Research intern at BAAI from February to June 2025, working with Dr. Hao Zhao.
Education
PhD student from January 2023 to present at 3DOM: FBK and University of Trento, supervised by Prof. Fabio Remondino; MSc from Hong Kong Baptist University; BSc from Guangdong University of Technology in China.
Background
Research focuses on multimodal 3D reconstruction (e.g., Gaussian Splatting), 3D generation, and scene understanding. Passionate about mentoring self-motivated junior students interested in advancing research in the 3D field.
Miscellany
Open to academic collaborations and communication at any time.