Tongyan Hua - 华 彤延

I am a Ph.D. student in the AI 4D City (AI4City) Lab at HKUST, Guangzhou, supervised by Prof. Wufan Zhao and Prof. Ying-Cong Chen. My current research interests focus on AI-based 3D computer vision. I have had the honour to collaborate with Prof. Wenming Yang at Tsinghua University and dear Prof. Addison Lin Wang at HKUST, working on knowledge distillation and Neural Radiance Fields (NeRF), respectively. Before this, I had extensively explored various research areas, including biotechnology, operational research, and geography, driven by pure interest. I was also a robotics algorithm engineer at Country Garden Group, focusing on visual SLAM for indoor construction robots.

I obtained my M.Sc. degree funded by three competitive scholarships at TU Delft and Leiden University. I completed my B.Sc. degree with the highest thesis score at Jiangnan University.

Email  /  GitHub  /  Google Scholar

Benchmarking Implicit Neural Representation and Geometric Rendering in Real-Time RGB-D SLAM
Tongyan Hua, Lin Wang.
CVPR 2024  /  Paper  /  Project

Implicit neural representation (INR), in combination with geometric rendering, has recently been employed in real-time dense RGB-D SLAM. In this work, we establish, to our knowledge, the first open-source benchmark framework to evaluate the performance of a wide spectrum of commonly used INRs and rendering functions for mapping and localization.

Hi-Map: Hierarchical Factorized Radiance Field for High-Fidelity Monocular Dense Mapping
Tongyan Hua*, Haotian Bai*, Zidong Cao, Ming Liu, Dacheng Tao, Lin Wang.
Pre-print  /  Paper  /  Project

In this paper, we introduce Hi-Map, a novel monocular dense mapping approach based on Neural Radiance Field (NeRF). Hi-Map is exceptional in its capacity to achieve efficient and high-fidelity mapping using only posed RGB inputs.