Zhuoling Li

Papers

Total Citations

H-Index

About

Zhuoling Li is a rising star in computer vision, whose research centers on unified monocular 3D object detection—a critical capability for applications like autonomous driving and robot navigation. Li’s most notable contribution is the development of UniMODE, a groundbreaking framework that, for the first time, enables a single model to perform 3D object detection across both indoor and outdoor scenes. This work addresses a fundamental challenge: training a unified model on diverse datasets, which often have vastly different characteristics (e.g., point cloud density, scale, and scene layout). By proposing innovative architectural designs and training strategies, Li’s approach achieves state-of-the-art performance on multiple benchmarks, demonstrating that a unified model can generalize effectively without sacrificing accuracy. Despite being published in 2024, UniMODE has already garnered 19 citations, signaling its rapid impact and adoption by the research community. Li’s work is particularly significant for real-world deployment, as it simplifies the pipeline for robots and autonomous systems that must navigate seamlessly between indoor and outdoor environments. With this foundational contribution, Zhuoling Li is poised to become a leading voice in the next generation of 3D perception research.