Chenxing Jiang

Hong Kong University of Science and Technology

Papers

Total Citations

H-Index

About

Chenxing Jiang is a leading researcher in real-time dense mapping for robotics, augmented and virtual reality, and digital twins. Their work centers on leveraging neural radiance fields (NeRF) to overcome key limitations in 3D reconstruction—specifically, the trade-off between reconstruction quality and real-time performance. Jiang’s most impactful contribution, the H2-Mapping system (2023, 35 citations), introduced a hierarchical hybrid representation that enables high-quality dense maps to be built in real time, a critical advance for autonomous navigation and immersive environments. Building on this, the H3-Mapping method (2024) further addresses the challenge of slow texture modeling by employing quasi-heterogeneous feature grids, pushing the boundaries of online mapping efficiency. With a total of over 40 citations across their top works, Jiang’s innovations are shaping the next generation of spatial intelligence systems. Their adaptive behavior research for quadruped robots on uneven terrain also demonstrates a broader interest in embodied AI. Jiang’s work is essential reading for anyone seeking to understand how implicit neural representations can be practically deployed in real-time, resource-constrained applications.